• One camp says base models are now good enough, just give them tools.

• Another (the moi is mostly in. it) says evaluation is the bottleneck, just build better judges.

While I would assign greater weight to the second camp, they are both directionally right and still too coarse.

The durable gains are showing up somewhere less glamorous and much more useful: new reliability knobs. Not one magical agent architecture, but a stack of control surfaces that help systems lose less intent, preserve more capability, remember more of the right state, and fail in ways teams can actually inspect and correct.

Several papers of note along these problems:

1. PPS: make intent explicit before the model starts guessing

Natural-language prompts have a hidden failure mode: intent transmission loss. The user knows what they mean; the model only sees the compressed, underspecified surface form. The PPS paper attacks that directly. Across 60 tasks, 3 domains, 3 models, and 540 generations, natural-language-rendered PPS outperformed both simple prompts and raw JSON on goal alignment. The gains were strongest in ambiguous business tasks, weaker in technical tasks, and actually reversed in low-ambiguity travel planning. That last part matters. It means structured prompting is not magic; it is most valuable when the user’s objective is fuzzy enough to be misread. The preliminary survey result is also practical: fewer follow-up rounds, from 3.33 to 1.13 on average.

Why we should care: a lot of agent failure is downstream of an upstream ambiguity. If the goal, audience, constraints, tone, and success criteria are hazy at turn one, the rest of the trajectory is just confident error propagation. The other useful lesson here is that raw structure is not enough. In the study, rendered PPS beat raw JSON. So the knob is not “add schema everywhere.” It is “make intent explicit in a form the model can actually use.”

Paper: https://arxiv.org/abs/2603.18976

2. Prompt repetition: a surprisingly cheap robustness hack

This one sounds silly until you think about what causal attention is doing.

The core idea is simple: when reasoning is not enabled, repeat the prompt. The paper shows that prompt repetition improved accuracy across popular models without increasing output length or materially increasing latency in most settings. On their experiments, it won 47 of 70 benchmark-model combinations with 0 losses when reasoning was disabled. The gains were especially strong when the prompt order was hostile to the model, such as options-first multiple choice, and on custom tasks like NameIndex and MiddleMatch.

Why we should care: not every model call inside an agent should be a long reasoning trace. Some calls are cheap subroutines: route this, extract that, normalize this, draft tool arguments, re-check the user constraint. For those non-reasoning calls, prompt repetition looks like a genuinely useful default knob. It is not a substitute for reasoning, and it is not free on arbitrarily long prompts, but for short operational subcalls it is exactly the kind of low-cost robustness trick teams tend to underrate.

Paper: https://ar5iv.labs.arxiv.org/html/2512.14982v1

3. GLM-5: do not buy agentic RL by deleting earlier skills

Sequential post-training has a nasty habit: each new stage can quietly sand down the thing the previous stage got good at.

GLM-5 is interesting partly because it says that out loud. Their pipeline runs sequential RL stages for reasoning, then agentic behavior, then general helpfulness, and then uses on-policy cross-stage distillation as a final refinement to recover skills from earlier stages. Previous stage checkpoints become teachers; the final pass is meant to stop the classic “more agentic, less sharp” tradeoff from becoming acceptable collateral damage. On their reported benchmarks, GLM-5 posts about a 20% average gain over GLM-4.7 across agentic, reasoning, and coding tasks, including 77.8 on SWE-bench Verified.

The more durable lesson is even lower-level than that. The paper is refreshingly explicit that agentic RL stability lives in systems details as much as in objectives. They switched to a deterministic top-k operator because nondeterministic sparse-attention selection caused sharp RL degradation, froze the indexer during RL for stability, and emphasized token-in-token-out handling so the trainer learns on exactly the same token stream produced by the rollout engine. That is the kind of detail that separates “agent demo” from “agent training system.”

Why we should care: a lot of agent improvement work still acts as if new capabilities can simply be stacked. In practice, they interfere. If post-training adds planning but dulls reasoning, or adds autonomy but destabilizes the learning loop, you have not really improved the agent. You just moved the failure somewhere harder to notice.

Paper: https://ar5iv.labs.arxiv.org/html/2602.15763v2

4. FullStack-Agent: round-trip the artifact, then test the hidden surfaces

I like this one because it attacks a very real agent failure mode: the frontend looks right, the demo works, and the backend is still fake.

FullStack-Agent combines three ideas. First, a multi-agent development workflow with specialized debugging tools for frontend and backend work. Second, FullStack-Bench, which evaluates not just frontend behavior but backend APIs and database state as well. Third, Repository Back-Translation, which converts existing real-world repositories into agent trajectories the model can learn from. The benchmark itself is notable: 101 instructions, 647 frontend tests, 604 backend tests, and 389 database tests. Even better, frontend success is not counted unless the required database interaction is real. That is exactly the kind of hidden-surface check agent evaluation needs more of.

The results are strong, but the more interesting pattern is the training and evaluation shape. FullStack-Dev with a Qwen backbone reached 64.7 frontend, 77.8 backend, and 77.9 database accuracy, while FullStack-Learn improved a 30B model through self-improvement using repository back-translation and augmentation. The debugging tools also mattered a lot: removing the backend debugging tool increased average backend iterations from 74.9 to 115.5. That is not just a model story. It is a workflow design story.

Why we should care: reliable coding agents need falsifiable artifacts. A useful practical extension of this idea is round-tripping: code to spec, spec back to code, compare the two, and inspect the mismatch. That creates a verifier surface instead of treating the codebase as one opaque blob. More broadly, the paper is a reminder that real artifacts and real tests are better teachers than synthetic vibes.

Paper: https://arxiv.org/html/2602.03798v1

5. MSA: memory should be part of the model, not a retrieval afterthought

Agents with long histories do not just need more context. They need memory that stays usable when the history becomes absurd.

MSA pushes that idea hard. The paper proposes an end-to-end trainable memory framework with sparse attention, document-wise RoPE, KV compression, and a Memory Parallel inference path. The headline is the kind of number people usually ignore until it becomes operationally relevant: less than 9% degradation while scaling from 16K to 100M tokens, with 100M-token inference on 2xA800 GPUs. The other important piece is Memory Interleave, which alternates retrieval, context expansion, and generation so the model can reason across scattered memory segments instead of just pulling one flat chunk and hoping.

Why we should care: a lot of current agent memory stacks are really retrieval pipelines wearing a memory costume. That works until the task needs long-range consistency, multi-hop evidence integration, or stable persona/state over time. MSA is interesting because it tries to make memory intrinsic and differentiable rather than bolted on. The real caveat is operational: the current setup still relies on offline pre-encoding of the corpus. So it is not a universal replacement for dynamic knowledge systems yet. But as a direction, it is much closer to agent memory than “just add bigger RAG.”

Paper: https://arxiv.org/abs/2603.23516

6. Verifier–compiler loops: verification is becoming its own stack

This is the one I keep coming back to.

The core production fact is ugly and simple: long workflows multiply small defects. In the verifier–compiler loop framing, a 1% failure rate across 100 steps leaves only about 36.6% end-to-end success. Even 0.1% per-step failure still leaves only about 90.5%. That is the march-of-nines problem. The implication is that agent reliability is not mainly a prompt problem. It is an error-correction problem. The system needs to observe the episode, judge it against institutional standards, intervene conservatively, replay changes before release, and keep durable evidence of what changed and why. That is also why the distinction between execution knowledge and institutional judgment matters: the agent can know the facts and still fail the organization.

Recent judge work mostly points in the same direction. JudgeBench shows hard evaluator tasks are genuinely hard, with strong models like GPT-4o only slightly above random on some challenging judge settings. RewardBench 2 makes reward evaluation meaningfully harder than RewardBench 1 and emphasizes correlation with downstream use. DeepSeek’s GRM/SPCT line is also important because it argues that reward modeling itself can scale with more inference compute through principle generation, critique, and voting, not just with bigger training runs.

But the field is also getting more honest about calibration. Evaluative Fingerprints found near-zero inter-judge agreement while also showing that judges are individually stable enough to be fingerprinted from their rubric behavior. In other words: they are not random, they are systematically different. Separate work on LLM-as-a-judge reporting shows that evaluator bias and uncertainty should be corrected statistically, not hand-waved. On user simulation, the news is similarly mixed: SimulatorArena suggests profile-conditioned simulators can track human judgments reasonably well on some tasks, but Lost in Simulation shows simulator choice can move measured success rates by up to 9 points and systematically miscalibrate difficulty.

Why we should care: one judge score is not a control system. High-reliability agents are going to need judge stacks, not judge monocultures: crisp gates for obvious defects, stronger reasoning judges for nuance, replay before release, disagreement review for hard cases, and humans on the highest-risk boundaries. Simulation will help widen coverage, but only if it is continuously calibrated against real traces.

Blog: https://www.equationblog.com/p/the-verifiercompiler-loop-turning

7. IndexCache: systems work is reliability work too

This one is more infrastructure than alignment, but it belongs in the same conversation.

IndexCache starts from a simple observation: in sparse attention, adjacent layers often choose very similar top-k token sets. So instead of recomputing the indexer at every layer, reuse it across layers. On the reported results, that removes up to 75% of indexer computation with negligible quality loss, while reaching 1.82x prefill speedup and 1.48x decode speedup at 200K context. The paper also reports 70–100% top-k overlap across adjacent layers, which is the structural reason the trick works.

Why we should care: efficiency is not separate from reliability. Every unit of inference cost you remove from the serving path can be reinvested into something reliability-shaped: longer context, more retrieval, more search, more verifier passes, more replay budget, or simply lower latency at the same control quality. That is why inference-side engineering keeps mattering more than people think.

Paper: https://arxiv.org/html/2603.12201v1

The connective tissue

If I had to compress the direction into one line, it is this: reliable agents are becoming layered control systems.

Structured intent reduces loss before the trajectory begins. Prompt repetition stabilizes cheap non-reasoning subcalls. Post-training methods like cross-stage distillation try to make new capabilities additive instead of destructive. Artifact-grounded training and hidden-surface testing make agent outputs more falsifiable. Long-memory work tries to decouple memory capacity from reasoning quality. Judge research is forcing evaluation to become calibrated, replayable, and auditable. Systems work buys the budget to do more of all of it in real time.

Just a growing stack of knobs that make agent behavior narrower, more inspectable, and a little less mysterious week over week.

That is the march-of-nines problem (as originally described by Andrey Karpathy). In a long workflow, tiny per-step defects compound into very large end-to-end losses. At 100 steps, a 1% failure rate at each step leaves only about 36.6% end-to-end success; even 0.1% still leaves only about 90.5%. For customer service, regulated operations, and multi-agent workflows, that gap is the difference between a promising demo and a system the business can trust.

The practical implication is that production reliability should be treated as an error-correction problem. Better base models help, but they are only part of the story. The system also needs a way to observe what happened, judge it against the organization’s standards, intervene safely when necessary, replay changes before release, and keep durable evidence of what changed and why.

Figure 1. In long workflows, small per-step errors compound into large end-to-end losses.

Reliability should come from continuously catching, correcting, compiling, and proving small errors — not from hoping one prompt patch will cover every edge case.

Production failures are not only knowledge failures

A surprisingly large share of production failures are not missing-fact failures. The agent may know the product terms, retrieve the right document, or call the right tool and still fail the institution.

Four surfaces matter in practice: missing knowledge, institutional judgment, user affect, and evidence. A response can be factually correct but still violate policy, choose the wrong level of certainty, worsen the user’s emotional trajectory, or leave the team unable to reconstruct what happened well enough to approve a safe fix.

• Missing knowledge: The agent lacks a fact, a tool result, or an updated policy exception.

• Judgment misalignment: The facts are present, but the trade-off between speed, certainty, empathy, policy, or escalation is wrong.

• Affect regression: The reply is technically valid but increases frustration, distrust, or confusion.

• Evidence gap: The team cannot replay the episode, inspect the rewrite, or approve the next release with confidence.

A banking example makes the distinction concrete. An assistant can know the product, know the account state, and still reply in a way that is too dismissive, too certain, or too slow to escalate.

Figure 2. A customer-facing answer can know the facts and still miss the institution’s judgment on policy, style, affect, or action.

Judgment should be explicit

One way to make this tractable is to keep execution knowledge and institutional judgment separate, but versioned together. Skills describe how the work gets done: task-specific success criteria, approved procedures, tool permissions, and required evidence. Judgment describes how the organization wants that work done: risk boundaries, policy rules, quality bars, tone, trade-offs, escalation behavior, and release gates.

That separation matters because business policy changes faster than workflow logic. If a new escalation rule or compliance boundary requires rewriting every skill from scratch, the system becomes brittle. If judgment is explicit, global changes can be compiled once and enforced across many workflows.

Figure 3. A reliable agent should keep workflow execution and institutional judgment separate, but versioned together as a behavioral contract.

An example of a production flywheel

A useful production flywheel is not a vague analytics dashboard. It turns one live interaction into an ordered, auditable episode. In one practical pattern, a conversation becomes: user message → draft response → affect and intent signals → initial evaluation → rewrite decision → post-rewrite evaluation → delivered message.

Once that structure exists, the same episode can be replayed later, reviewed by humans, approved or rejected, and compiled into the next version of the behavioral contract. Runtime interventions can stay conservative — rewrite, route, pause, slow-halt, or escalate — while the offline loop decides what should become a durable product change.

This is the shift from prompt folklore to production engineering. A corrected response is useful at the moment; a replayable, reviewable correction is useful week over week.

A few operating patterns tend to work

• Observe real traces, not only synthetic eval sets.

• Keep affect, policy, and tool behavior in the same episode view.

• Replay proposed changes before release rather than patching blindly in production.

• Treat approvals and evidence as part of the product, not as after-the-fact documentation.

Figure 4. A production flywheel turns one conversation into an ordered, replayable episode that can be inspected, approved, and released with confidence.

Judge quality now depends on calibration

Recent judge research points in two directions at once. On one hand, judges are improving. Benchmarks such as JudgeBench and RewardBench 2 are making judge quality easier to measure, while DeepSeek’s GRM / SPCT work suggests that principle generation, critique, and inference-time aggregation can make reward modeling and preference judging much stronger in practice.

On the other side, the field is getting more honest about calibration. Newer 2025–2026 work argues that one raw judge score is not enough. Some evaluators show stable but different “evaluative fingerprints,” meaning they can be internally consistent while still disagreeing systematically with one another. Other papers show that rubric order, pointwise versus pairwise framing, and judge allocation can shift rankings if those choices are left uncalibrated.

The production lesson is simple: one judge should not be the whole control system. High-reliability systems tend to use a judge stack — crisp gates for clear defects, calibrated reasoning judges for nuance, replay for release decisions, disagreement review for hard cases, and humans for the highest-risk boundaries.

The newest question is no longer only “Which judge scores highest on a benchmark?” It is also “Which judge remains stable, interpretable, and properly calibrated inside a release process?”

User simulation can help, but only with calibration

User simulation is becoming necessary because replay without synthetic users does not cover enough edge cases. Recent work such as SimulatorArena suggests that profile-conditioned simulators can track human ratings reasonably well on some multi-turn tasks, especially when the simulator has access to richer user profiles rather than a generic system prompt.

But simulation should not be treated as ground truth. Lost in Simulation is the warning label: simulator choice can materially change measured success, and simulated populations can drift away from real human behavior. The practical pattern is simulation plus calibration — use synthetic users to widen test coverage, then measure the gap to hold-out human traces and correct for it.

Auditability should be part of the product

If the team cannot reconstruct which draft was blocked, which rewrite was sent, what evidence triggered the intervention, and which version of the behavioral contract approved the change, then it does not really have a production flywheel. It has prompt folklore.

Auditability is what turns one corrected episode into a durable release decision. In practice, that usually means keeping trace and event correlation, judge verdicts, rewrites, replay results, approval records, and release decisions together. The goal is not paperwork. The goal is to make the next change easier to inspect, safer to ship, and easier to trust.

How this connects to my ODSC East talk

At ODSC East 2026, I’ll go deeper into the mechanics behind this pattern: how judge stacks can be calibrated, how runtime interventions can be chosen without creating new risk, how replay should precede release, and how week-over-week improvements can turn human preferences into durable production agent judgment.

The talk title is “The Verifier–Compiler Loop: Turning Human Preferences into Production Agent Judgment.” This article only sketches the frame. The session will go much deeper into the system design and operating model behind it.

Selected references

• JudgeBench

• RewardBench 2

• Inference-Time Scaling for Generalist Reward Modeling (DeepSeek GRM / SPCT)

• How to Correctly Report LLM-as-a-Judge Evaluations

• Evaluative Fingerprints: Stable and Systematic Differences in LLM Evaluator Behavior

• Who can we trust? LLM-as-a-jury for Comparative Assessment

• SimulatorArena

• Lost in Simulation

But if you ship agents, you learn a painful lesson fast:

An agent that succeeds once is not a reliable agent.

Single-run success rates are demo metrics. Production reliability is a different game:

1. Consistency across runs (the same task, same setup, multiple attempts)

2. Robustness to “equivalent” user inputs (paraphrases, small spec changes, harmless reorderings)

3. Grace under tool/API failures (because they will fail - timeouts, rate limits, partial responses, schema drift)

4. If I had to compress the theme of the last ~90 days into one line, it’s this:

Reliability is a surface, not a score.

This post is intentionally narrow: recent work that treats agent reliability as a first-class object - not a vibe.

The production reality check: humans are still the reliability layer

A paper I keep pointing people to is “Measuring Agents in Production.” It’s one of the rare efforts that asks practitioners what’s actually working (and what’s breaking).

A few findings that stuck with me:

• Many production agents are built to be simple and controllable: 68% run at most 10 steps before requiring human intervention.

• Most teams lean on prompting off-the-shelf models vs weight tuning (70%), and rely primarily on human evaluation (74%).

• Reliability shows up as the top challenge - especially “ensuring and evaluating correctness.”

That’s the current equilibrium: humans as circuit breakers.

The real question is how we scale beyond that without lying to ourselves about what “reliable” means.

ReliabilityBench: measuring reliability as a surface, not a score

ReliabilityBench is exactly the kind of benchmark we’ve needed.

Instead of asking “did it succeed,” it asks:

1. Does it succeed again (consistency)

2. Does it succeed under equivalent variations of the task (robustness)

3. Does it survive tool/API failures (fault tolerance)

They formalize this across three dimensions:

• pass^k for repeated execution

• perturbation intensity ε

• fault intensity λ

• ...and propose a unified reliability surface: R(k, ε, λ).

Two ideas here that I think will stick:

1. Action metamorphic relations: judge correctness by end-state equivalence rather than brittle text matching.

2. Chaos-style fault injection: simulate timeouts, rate limits, partial responses, schema drift.

The reported results are the point:

1. Perturbations alone reduced success from 96.9% at ε=0 to 88.1% at ε=0.2.

2. Rate limiting was especially damaging.

This is what “production-like” really means: not one clean run, but performance under stress.

Why we should care:

1. If you only track single-run pass rates, you end up optimizing for demos.

2. A reliability surface forces the conversation into repeatability, robustness, and failure modes.

E-valuator: turn “judge scores” into runtime decisions (with guarantees)

Assume you’ve built a verifier (LLM judge, PRM, heuristics). You can score trajectories - but can you trust the score enough to make a runtime decision?

E-valuator reframes this as a sequential hypothesis testing problem: distinguish successful vs unsuccessful trajectories as actions unfold, using a statistically valid test at every step.

They propose converting any black-box verifier score into a decision rule with controlled false-alarm rates, and show it can both improve monitoring and terminate problematic trajectories early to save tokens.

Why we should care:

1. “Judge reliability” is now a core dependency for agent reliability.

2. This is one path from heuristics to operational control.

LLMdoctor: test-time steering as a reliability tool

Benchmarks and verifiers tell you “it broke.”

But reliability also requires you “fix it now.”

That’s why I like test-time alignment approaches that are modular. LLMdoctor has a clean patient-doctor framing: steer a frozen model with a smaller controller trained on token-level preference signals, via token-level flow-guided preference optimization.

Even if you ignore the specific algorithm, the pattern matters:

1. You can steer without retraining the foundation.

2. You can make reliability interventions fast and reversible.

3. You can version and evaluate the controller like a product.

Why we should care:

• Most teams treat reliability fixes as either “change the prompt” or “fine-tune and pray.”

• Controller-style steering gives a third option: a scoped, testable intervention layer.

Human-in-the-loop rubrics: reliability is often a “shared standard” problem

The hardest part of agent reliability isn’t always the model.

Sometimes it’s the absence of a shared, auditable definition of “correct.”

A recent paper on patch evaluation proposes a simple but scalable framework:

• use an LLM to draft a task-specific rubric,

• have a human review/refine it once,

• use the rubric-guided LLM judge to evaluate many candidates.

They report improved agreement with human consensus (e.g., Cohen’s kappa 0.75 on the subset with unanimous human agreement), plus high recall/precision in that setting.

Even though the domain is program repair, the reliability lesson generalizes:

When humans disagree, it’s often because the rubric is implicit. Make it explicit once - then scale it.

A narrow reliability loop I’d actually run

If I had to condense the above into a practical loop (without turning it into a platform pitch), it would look like this:

1. Define correctness in end-states, not text: Use metamorphic relations / end-state equivalence where possible.

2. Stress-test, don’t just benchmark: Measure a reliability surface across repeated runs (k), perturbations (ε), and tool failures (λ).

3. Monitor online with calibrated decision rules: Turn verifier scores into stop / continue / escalate decisions you can defend.

4. Keep humans as reviewers of standards, not full-time graders: Use human time to approve/refine rubrics and resolve disagreements.

5. Treat steering as a first-class intervention: Controller models (doctor -> patient) are a pragmatic way to improve behavior without turning every fix into a full retrain.

Agent reliability is not a single feature and not a single metric. It’s a contract:

1. measured under stress

2. monitored online

3. improved with small, controlled interventions

4. audited through shared standards humans can actually read.

The best recent work is finally treating reliability like an object we can engineer - not a hope we can prompt.

Quick credit: Andy Wong consistently finds great new papers early, and we end up debating the implications together before they show up in writing.

Most weeks, the discourse around language models collapses into one of two modes:

• “Look at this new leaderboard bump.”

• “Agents are coming, everything changes.”

Both can be true - and still miss the point.

The stuff that actually moves production outcomes tends to look like new control knobs: better ways to steer models, keep them stable, make them faster, and make failures more legible.

Credit where it is due: a bunch of these paper finds came from Andy Wong, who consistently surfaces great work. We usually end up debating the implications together before it shows up here.

So here is my January reading stack: papers that feel unusually primitive-shaped. Each one adds a knob I expect we will keep using.

1. Recursive Language Models: “infinite” context via self-calls (no retraining)

Recursive Language Models (RLMs) are a different answer to long context: do not cram the prompt into the transformer - treat it like part of the environment.

One concrete instantiation: the prompt becomes a variable inside a Python REPL, and the model writes code to inspect the prompt, decompose it, and recursively call sub-instances of itself over slices of the prompt.

They report handling inputs two orders of magnitude beyond typical context windows - and even mention strong performance at the 10M+ token scale.

Why we should care:

• This pushes long context from architecture into systems. Not ‘train longer,’ but ‘reason out-of-core.’

• It is an agent-shaped pattern: when the model can write the loop it thinks inside, you get a new class of tool-use + decomposition behaviors.

It reframes the bottleneck: the limit becomes less context length and more how good the model is at building the right indexing + recursion strategy.

2. LLMdoctor: alignment at test-time, token by token

Most alignment work still assumes you either fine-tune the whole model (expensive, slow, often brittle), or you do test-time tricks that are coarse (trajectory-level) and compute-hungry.

LLMdoctor proposes a clean separation: keep a big ‘patient’ model frozen, and steer it with a smaller ‘doctor’ model using token-level signals.

Their claim is that many test-time alignment methods rely on distorted trajectory-level rewards or inefficient sampling that caps performance and harms diversity. The patient-doctor setup extracts token-level preference signals from the patient’s behavioral variations, then trains the doctor via token-level flow-guided preference optimization (TFPO) to preserve diversity while aligning outputs.

Why we should care:

• Steering becomes modular. Iterate on the doctor without re-baking the patient.

• Granularity matters. Token-level intervention is the difference between ‘mostly aligned’ and ‘aligned where it counts.’

Closer to how agents fail. Agents do not fail at the end of the trajectory - they fail mid-trajectory.

3. Entropy-Adaptive Fine-Tuning: a practical take on “don’t forget”

Supervised fine-tuning is still the workhorse for specialization - and “catastrophic” (or I would rather say “annoying”) forgetting is still the bill we pay.

This paper’s framing is crisp: it contrasts SFT with on-policy RL and argues the gap comes from distribution mismatch. In RL, the model’s learning signal is more consistent with its internal beliefs; in SFT, the model is forced to fit external supervision even when that conflicts sharply with what it ‘knows.’

They focus on confident conflicts: cases where the label token is low-probability under the model, while the model’s distribution is low entropy (i.e., it is confidently predicting something else). That is where gradients get destructive.

Their proposal, Entropy-Adaptive Fine-Tuning (EAFT), uses token-level entropy as a gating mechanism: learn aggressively when the model is uncertain; suppress gradients when the model is confident-but-disagreeing.

From my most recent post: I also think EAFT is a genuinely useful alternative to LoRA in the ‘don’t wreck the base model’ sense - rather than constraining where we update (parameter-efficient adapters), EAFT constrains when updates should matter (skip the destructive ones).

Why we should care:

• This is the kind of idea that turns continuous updates from scary to feasible.

• It maps to a real production vibe: most of the time we want to learn; sometimes we want to refuse the lesson.

• It is a different safety knob than LoRA - but it is targeting the same anxiety: regressions.

4. From Entropy to Epiplexity: measuring “useful information” for bounded learners

Data quality is still the hidden kingmaker. The hard part is: we are not data-rich, we are signal-poor.

This paper asks a deceptively simple question: can we quantify learnable content in data without tying it to a downstream task?

They argue classic information measures (Shannon entropy, Kolmogorov complexity) do not capture what matters for computationally bounded learners, and they propose a new measure: epiplexity.

The vibe: epiplexity is meant to capture structural content while excluding ‘time-bounded entropy’ (random/unpredictable content), and the authors claim it helps explain why deterministic transformations and data ordering can still create useful learnable structure in practice.

Why we should care:

• If inputs are becoming the product, we eventually want a metric for the informational value of inputs.

• Epiplexity feels like a step toward data selection as an engineering discipline, not an art project.

5. LLaDA2.0: diffusion language models to 100B

Autoregressive decoding is powerful, but it is fundamentally serial.

LLaDA2.0 pushes discrete diffusion language models to 100B parameters via a conversion process: take a pretrained AR model and convert it to a dLLM using a 3-phase block-level training scheme (warm-up with increasing block size, stable full-sequence diffusion, decay back to compact block diffusion).

They also discuss post-training alignment with SFT and DPO, framing this as a path to frontier-scale efficiency while preserving parallel decoding advantages.

Why we should care:

• Parallel decoding is not just a speed story. It changes how we can spend compute at inference time.

Faster sampling = more room for verification, search, and self-checking within real latency budgets.

6. PoPE: decoupling the “what” and “where” in positional embeddings

I have a soft spot for papers that say: ‘this popular thing is entangled in a way that quietly hurts you,’ and then fix it cleanly.

PoPE (Polar Coordinate Positional Embeddings) argues RoPE entangles content (what) and position (where), which can impair tasks requiring independent matching on the two. They propose PoPE to remove the confound, show better performance on diagnostics and across sequence modeling domains, and highlight strong zero-shot length extrapolation vs RoPE - and even vs YaRN.

Why we should care:

• Long context is now table stakes for serious agent workflows.

• Works at 8k is not the same as behaves at 80k.

DeepSeek + stuff that ships

Engram: conditional memory as a second sparsity axis

The Whale does it again. MoE gave us conditional computation. But knowledge lookup is still mostly simulated via dense compute.

Engram proposes conditional memory - a complementary axis of sparsity - implemented via an O(1) lookup module modernizing classic N-gram embeddings.

They describe a ‘Sparsity Allocation’ tradeoff between neural computation (MoE) and static memory (Engram), claim a U-shaped scaling law, and report scaling Engram to 27B parameters with gains not just on knowledge tasks but also reasoning, code/math, and long-context retrieval.

mHC: Manifold-Constrained Hyper-Connections

This zooms in on a real training pathology: expanding residual streams/connectivity can improve performance, but it can also break the identity mapping property residual connections rely on - leading to instability and scalability issues.

mHC proposes projecting the residual connection space onto a manifold to restore identity mapping while keeping things efficient.

DeepSeek-R1: RL-first reasoning + the GRPO refresher

Even if you are excited about the next base model drop, R1’s training recipe is the more durable lesson.

The core claim: reasoning behaviors can emerge via pure RL (with a cold-start SFT phase for readability/stability), and they lean on GRPO - which is worth revisiting if your PPO mental model is rusty.

Quick intuition: GRPO drops the critic and estimates a baseline from grouped samples, which matters a lot for scaling RL in LLM land.

Solving LLM repetition in production

This one earns points for being unapologetically real: repetition loops that stall batch tasks.

They identify repetition patterns, frame the root cause via Markov analysis + greedy decoding getting stuck in loops, and evaluate mitigations: beam search with early_stopping=True (universal post-hoc), presence_penalty (case-specific), and DPO fine-tuning (model-level universal).

The connective tissue

If I had to summarize the direction across these papers in one line: we are entering the era of systems that add knobs: inference-time recursion for extreme context, token-level steering, entropy-gated learning, explicit memory, better information measures, disentangled position representations, and faster decoding.

The fun part: these knobs compound.

“What is your Product Development Process?” - I’ve been asked this question several times lately—including during the ELC podcast.

I’ve always been an engineering person. Systems, infrastructure, APIs—that’s the way my brain was wired. My interest in product and users started early at LinkedIn. Perhaps I was influenced by my product partner there - Allen Blue, who was one of the co-founders and amazingly forward looking product visionary. Somewhere in those early cycles it clicked: we do what we do in service of our users—whether those users are developers, end users, or enterprise customers. That realization pulled me from “just engineering” into caring about product outcomes. And yet, at the start, I was a complete novice at product (and truthfully probably still am).

I read the usual suspects (The Lean Startup, Competing Against Luck, The Mom Test, and a mountain of blogs) about experiments, rapid iteration, speed, listening to customers, etc. Yet the truth is that a lot of product and company building is about luck—and if you play the lottery long enough, sometimes you win and the technique was perhaps less important than professed. At some point I came to a realization: there is no such thing as “finding” product‑market fit beyond random luck. There is only compelling the world to accept your vision of the future.

So, here’s how I think abut the product product development process today:

1. Imagine the future

Think of yourself as a sci‑fi writer. Imagine the future you want to see. In detail and with maximum nuance. Feel it, smell it, live it, write about it (for yourself mostly). This is not entirely a logical process. Works of art don’t come from the mind alone; they come from the soul. The more exact, detailed, and precise the imagination—the better. The approach works not only for big ideas, but also for small problems, design decisions and similar challenges. Try it. Obviously, you need a background in the field so your imagination has grounding.

Where this can go wrong:

• The idea isn’t yours. Works of art are not a collective exercise. We often adopt other people’s ideas unconsciously—we are imitators by design (see René Girard’s mimetic theory). Your founding team can absolutely enhance and improve the idea—just don’t confuse where it came from. Maybe the product idea isn’t yours, but you came up with a technological solution that makes it work—that’s OK, join the team. The worst failure mode is convincing yourself you like someone else’s idea on logical merits when you’re not passionate about it. If you’re going to be a mercenary, be honest about it—and love the craft of being a mercenary.

• The idea isn’t well envisioned. It’s a fleeting, fuzzy thought. The world can’t materialize a fuzzy image. This failure mode often happens to non-technical people or when we simply don’t yet have a necessary background to be able to imagine the end product in a precise enough detail.

• It’s purely cerebral. A product born only from logic usually isn’t art. You need conviction that lives below the neck.

2. Test it

Pitch it to your smartest friends, as well as to friends not in the field. Stress‑test it from different angles. Run experiments to prove or disprove your thinking. Is the idea actually new in the first place or you just didn’t bother to do basic research? Think like an investor; evaluate it as you would an investment pitch. This is the logical part. Is the technology feasible? Is the timeframe right? You have to allow some uncertainty, perhaps a lot of uncertainty. You will hear many “no”s and there will never be enough data. But there should be a threshold of probability you can settle on—and then decide.

Where this can go wrong:

• No serious scrutiny. Less of an issue with startups, but a very common failure mode in large companies. Apply VC‑type scrutiny: explicit assumptions (why, why now, why this team, how is it different, what category are we creating or capturing, how do we solve the distribution). Even for small projects - do this, it can be done very quickly with modern tools.

• Never‑ending search for 100% conviction. It doesn’t exist. Set the risk level you can carry and move.

3. Focus on it

This is about compelling the world to accept your vision. It requires assembling as many smart, values‑aligned people as you can and maintaining persistent focus on execution. This is also the place where much traditional advice can work—to an extent.

Where this can go wrong:

• Insufficient critical mass of smart people, or settling for the wrong, mediocre team (or a team of mercenaries) that isn’t excited or hasn’t adopted the idea almost as a new religion. I have yet to hear from anyone that they have a mediocre team (“we have a very high bar cliché”). Be honest, is it really true? Most teams in fact are mediocre or worse.

• Insufficient funding. It is perhaps a sad truth - but funding is a competitive differentiation for startups. Inadequate capital could impair both the ambition and execution when the speed matters most.

• Loss of focus during execution. Could happen for variety of reasons - loss of conviction on a part of the team, poor growth execution / team dilution (by hiring too many or wrong people too fast), sometimes a function of too much funding.

• Bailing too early—not giving the idea enough time to work. This one is hard as you never know for sure.

I’m writing this for myself—as a reminder—as much as for you. It’s incredibly easy to fall into these traps.

Imagine clearly. Test honestly. Focus completely.
Compel the world.

Love to hear your thoughts.

If you watch today’s agents for more than a few minutes, you see the mood swings. In one chat they’re warm and crisp; in the next they over‑explain, miss an obvious cue, or bungle a tool call with the wrong parameter. And even when there’s no “human feel” at all—just a heads down task—they drift off spec: skip required steps, optimize the wrong objective, or simply neglect or misinterpret human inputs.

I don’t think this is a “just scale it” problem. It’s a feedback problem. We’re still treating behavior—tone, choices, task adherence, even API hygiene—like vibes in a prompt instead of something we can observe, grade, and steadily improve. That’s why I keep coming back to intelligent data flywheels: small, concrete loops that turn context ↔ behavior trace into a living artifact for training, evaluation, and live steering.

What I mean by “intelligent data flywheels”

The picture in my head is simple. Keep a map of the situations your agent encounters (support vs. sales, calm vs. upset, low‑stakes vs. high‑stakes) and the behaviors you want in each (clarity, empathy, brevity, caution, brand voice and values). Use that map to (a) generate realistic multi‑turn data—by having a “Human LLM” act out the human side of conversations—and (b) judge the agent against the behavior playbook with a grader that you also train. Then run the same primitives at three speeds: observability (find where it breaks or excel), inference‑time nudging (steer it right now), and training (make the fix stick). When human raters and the judge disagree beyond a reasonable margin, you update the judge; when they align, you let the judge carry more load and feed the next enhancement round. That’s the loop.

I still care a lot about emotional intelligence—human-facing agents that communicate across different media and modalities—but the same flywheel helps with boring, high‑impact stuff that isn’t “EQ” at all: tool use, retrieval grounding, latency/cost tradeoffs, and safety drift.

Why this suddenly feels practical

A few research threads clicked into place:

• Principle‑following reward models showed you can align behavior to a collection of human-written rubrics instead of massive preference sets

• Inference‑time scaling for judges matured (e.g. DeepSeek’s GRM). Spend more tests‑time compute—parallel samples plus a meta‑judge—and you get more reliable reward signals for both training and live guardrails.

• Judges that actually reason generate a case-specific rubric before scoring, which humans can verify, align, and generalize..

• Open, strong preference data (e.g. helpsteer3) and closed, experiential data from your deployed agent provides a solid base you can specialize with your own behavior map.

Caveat: LLM‑as‑a‑judge isn’t magic. Benchmarks like JudgeBench show judges can be brittle or biased if you don’t treat them like first‑class products—versioned, monitored, retrained, and contexted.. That’s another reason to put them inside the flywheel.

The unglamorous stuff agents fail at

• Function calling & schema correctness. Even top models still fumble basic format rules (quote this string; ISO date there) and multi‑step tool chains. Recent work—BFCL, JSONSchemaBench, IFEval‑FC—quantifies how often calls are syntactically valid yet semantically wrong. In my head, the “judge” can be a schema/trace checker with scenario‑aware penalties, and the generator can synthesize tricky, long‑horizon tool graphs to close the gap.

• Grounding & hallucinations in RAG. Datasets like RAGTruth and newer lenses like HalluLens keep reminding us that extrinsic hallucinations haven’t vanished; high‑certainty hallucinations are especially sneaky. A flywheel can grade answers on entailment against retrieved context and choose the next hard cases to label or synthesize.

• Open‑world task reliability. Real agent work looks like OS‑level workflows and the messy web. OSWorld, WebArena, and AgentBench have moved the bar here and highlight recurring failure modes—state tracking, planning depth, visual grounding. Using their task taxonomies as “contexts” and step‑level success as “behaviors” gives you a clean contract for the flywheel to optimize.

• Safety and the “persona dial.” OpenAI’s emergent‑misalignment results point to interpretable persona features—directions in activation space that modulate toxic or deceptive modes. That turns safety from a black box into a dial you can monitor and counter‑steer inside the flywheel.

And yes, EQ still matters because humans are in the loop. Benchmarks like EmoBench, EmotionQueen, and multimodal EmoBench‑M show a persistent gap to humans on “understand + respond appropriately.” That’s the sweet spot for a behavior‑by‑context map coupled to a judge that also reasons about emotion.

How this looks in practice—my mental movie

I picture an analytics view that doesn’t just say “CSAT dropped,” but where and why: “In escalations from upset users, brevity overrode clarity; schema errors spiked in step‑3 tool calls; the judge drifted on empathy.” From there, the loop suggests more of what it needs: a batch of synthetic escalations with complicated tool chains; a judge tune on Emotion‑Application items; a tweak to the behavior weights for this scenario. We close the loop in three places: surface the issue (observability), compensate now (inference), and make it permanent (training). Publish the change, re‑benchmark, repeat.

Over time you get a system that not only thinks better, but behaves predictably under stress—because behavior stopped being vibes and started being data.

And one more thing: over time, those results compound into a differentiated, market-adapting playbook — a living operational memory co-built by your team and the system, shaped by every success, failure, and fix.

The constraints we actually fight

Most of engineering is just pressure-testing three constraints: human cognition (complexity, coordination, bugs), provisioning at scale (deploy, redundancy, cost), and change risk (feedback loops). The tools that moved the needle before LLMs—managed runtimes, DVCS+CI/CD, containerization/cloud, observability—were all bets against those constraints.

What shifted with LLMs

Treating the model like a “compiler” works—until it doesn’t. Traditional compilers are deterministic; auto‑regressive models aren’t. Tiny prompt edits (or swaps between model families) yield materially different outcomes. That puts inputs—prompts, retrieval/context rules, tool schemas—and evaluation at the center. The inputs are the product.

Two practical implications:

1. Inputs as first‑class artifacts.
   Prompts (and flows), input datasets (docs, tickets, logs), models/fine‑tunes, and eval suites/user simulators all need real versioning, lineage, and regression checks—because models change under your feet.

2. Evaluation is your safety rail.
   You won’t guarantee determinism; you can bound behavior and catch drift. Invest in evals and forward simulation before you put agents anywhere near money or production.

Legacy, repos—and the new “rewrite”

“Full rewrite” used to be a dirty word. With LLM‑accelerated throughput, wholesale rewrites are increasingly viable when entropy makes understanding costlier than regeneration + hardening with evals.

What engineering is becoming

Zoom out and the job collapses into tooling and data.

Humans become what the models aren’t: (a) evaluators and (b) carriers of undocumented institutional knowledge. That’s where leverage lives.

Tech debt is dirty data.
Clean it, or it compounds.

A minimal operating checklist (until better tooling is available):

• Check in prompts with code. Include tool schemas, context rules, guardrails, and tests.

• Pin and record models. Track families/versions and fine‑tuning metadata like compiler flags. Expect drift.

• Build evals before features. Scenarios, simulators, acceptance criteria—gate releases on them.

• Prefer rewrite when entropy wins. If understanding cost > regeneration + eval hardening, start over.

• Instrument everything. You can’t lead probabilistic systems blind.

None of this requires prophecy (Bohr and Feynman would approve); tempered by the reminder that auto‑regressive generation diverges without control.

The link to the full video

— Ruslan

As mentioned in the previous post - I’ve recently tweaked my workout schedule to harmonize the functional block (focused on full body power movements) and weight lifting block (focused on muscle building) to make them both be 6-weeks in length each. I alternate those blocks.

In my previous post I described the prior routine: two blocks — a 6-week full-body (mostly power-focused) functional block, followed by a 4-week weight-lifting block.

In this post, I’m outlining a modified functional block. This is the hardest block due to high demand on neuro-musculature system (even though the weights are considerably lower) and the follow on weight lifting block always feels like a break.

As before, I work out first thing in the morning (work scheduling), with a 5:30 am wake-up, quick oral/face hygiene, pre-workout supplements, and a 10-15 min meditation.

Because the blocks are now a bit longer, I’m skipping pre-workout foam rolling during the work week. If I had unlimited time, I’d keep it.

I still use guided workouts (Beachbody — historical) mainly for timing and pacing.

The core workout is built around The 6-weeks of the work program by Amolia Ceasar and it consists of 3 blocks, 2 weeks each. The workouts get progressively more complex (although not necessarily harder) in each subsequent block. Since the program has a formal rest day and a really easy 20-25m stretch routine day, I simply skip the rest day and tag on the stretching routine to the tail end of the last workout of the week. So the program’s 2 weeks end up being 10 days for me. To make it still be 6 calendar weeks I simply repeat week 1 or week 5 in the end (week 1 is actually one of the hardest weeks if you push the weights up). For reference - I am sharing my workout sheets here.

Below are two blocks each matching alternating week in the program.

Weeks 1/3/5:

Weeks 2/4/6:

• P90X3 Challenge consists of four blocks. Each block has two sets of pull-ups followed by push-ups (different variations). My current numbers are: 15 pull-ups, 40 push-ups per set. That’s 120 pull-ups and 320 push-ups per workout. There’s also a burnout at the end — 2 pull-ups and 4 push-ups, no rest, for 6 sets — so add 12 pull-ups and 24 push-ups to the total.

• 10min Ab Hummer is from Hammer and Chisel program, P90X Ab Ripper is from P90X and 10min Abs is from Insanity Max 30.

Intervals

• Long intervals: 3-min warm-up jog; 3 × 5-min runs with 2-min walks in between; cool-down jog/walk.

• Short intervals: 3-min warm-up jog; 9 × 1-min max-effort sprints with 1-min walks; cool-down jog/walk.

• When time is short, abs get dropped first. If Zone 2 is 50 min, I cut it to 30; if Zone 2 follows intervals, I drop it.

The form is critical for these workouts, especially mental fatigue sets in. Seemingly lower weights can be deceptive - do not raise the weights unless you can complete the exercise with nearly a perfect form, as the risk of injury with complex power moves goes up considerably.

Note: doing exercises with a perfect form is an easy way to enhance effectiveness with lower weights and much reduced risk of injury.

When traveling

When traveling and the hotel gym with weights is available, both circuits can continue, depending on the space and how crowded the place is. When no gym is available I normally switch to Insanity Max 30 Month Two workouts for the duration. Those are body weight only and while not sufficient by themselves, they are decent enough for maintenance while traveling.

Again - this is what I do. Consistency and a purposeful plan are keys and there are many other ways to stay in shape.

DEXA Update (August, 2025):

As you can see - total body fat went up by 3.3 pounds, while total lean mass went up by 4.4 pounds since the last scan. As you can see - it is actually very difficult to increase lean mass without gaining some fat mass.

I’ve recently tweaked my workout schedule, shifting more toward muscle and VO2max maintenance.

In my previous post I described the prior routine: two blocks — a 6-week full-body (mostly power-focused) functional block, followed by a 4-week weight-lifting block.

In this post, I’m outlining a modified weight-lifting block that’s now 6 weeks to match the functional power block.

As before, I work out first thing in the morning (work scheduling), with a 5:30 am wake-up, quick oral/face hygiene, pre-workout supplements, and a 10-15 min meditation.

Because the blocks are a bit longer, I’m skipping pre-workout foam rolling during the work week. If I had unlimited time, I’d keep it.

I still use guided workouts (Beachbody — historical) mainly for timing and pacing, and my week starts on Sundays.

The general structure: a weight-lifting segment followed by a cardio segment (where I listen to podcasts or other educational audio).

• The core workouts are built around Body Beast workout with additional components added on.

• P90X3 Challenge consists of four blocks. Each block has two sets of pull-ups followed by push-ups (different variations). My current numbers are: 15 pull-ups, 40 push-ups per set. That’s 120 pull-ups and 320 push-ups per workout. There’s also a burnout at the end — 2 pull-ups and 4 push-ups, no rest, for 6 sets — so add 12 pull-ups and 24 push-ups to the total.

• T-30 Chin-up and Pull-up routines are short (~12m) 2X chin-up/pull-up ladders followed by hanging leg raises, monkey bar simulation and a burn-out. My ladder is usually 2-4-8-16 (30 total in each ladder).

When time is short, abs get dropped first. If Zone 2 is 50 min, I cut it to 30; if Zone 2 follows intervals, I drop it.

Intervals

• Long intervals: 3-min warm-up jog; 3 × 5-min runs with 2-min walks between; cool-down jog/walk.

• Short intervals: 3-min warm-up jog; 9 × 1-min max-effort sprints with 1-min walks; cool-down jog/walk.

Notes on the weight-lifting pattern

Standard sets follow a light–medium–heavy–drop-set pattern.

• Light set (15 reps): warm-up for the muscle group and a chance to fine-tune the form.

• Medium set (≈12 reps): calibration (heavy but not maximal). Sometimes I skip medium and go straight to a heavy 8-rep set, then a second heavy set after 45–60 s rest.

• Heavy set (6–8 reps): stop 1–2 reps shy of failure, immediately followed by a drop set at medium weight for another 6–8 reps.

There are no true power moves in this block, but I often simulate them by moving fast on the concentric and slowing down on the eccentric (e.g., a rapid pull-up followed by a slow controlled descent).

Note 1: doing exercises with a perfect form is an easy way to enhance effectiveness with lower weights and much reduced risk of injury.

Note 2: shoulder upright row is bio mechanically not a great exercise as it puts shoulders into an impingement position (EZ-bar or not), so I replace it with a dumbbell high pull as the closest alternative.

As always—if the last set is too easy, add a few extra reps; next time, increase the weight. The key to performance is sufficient stimulus.

This direct integration makes data quality crucial. Fine-tuning can deliver significant improvements in accuracy and domain alignment, but only if the training data is both reliable and relevant. Unfortunately, many enterprise datasets—sourced from CRMs, ERPs, and other operational systems—are incomplete, inconsistent, and lack clear indicators of quality. These repositories often contain “dirty” data that, even after cleaning, remains difficult to differentiate in terms of importance or strategic value. Merely connecting an LLM to these data sources, hoping they will serve as a source of refined knowledge, is insufficient. Without a methodology to identify which subsets truly matter, organizations risk overwhelming the model with undifferentiated content, ultimately diluting its domain expertise rather than enhancing it.

Only with robust frameworks for scoring, filtering, and weighting data can organizations ensure that their fine-tuned LLMs prioritize the most accurate, timely, and contextually relevant information. In the absence of these data differentiation strategies, the promise of fine-tuning remains out of reach, and valuable proprietary knowledge fails to translate into tangible performance gains for the AI model.

An Even Bigger Problem: Human Knowledge Gaps

Even if enterprise data could be perfectly cleaned, quantified and integrated, it still wouldn’t guarantee optimal AI-driven decisions. A significant portion of critical knowledge remains locked in human minds—varied in expertise, judgment, and subjectivity. This disparity is why organizations hold meetings, rely on structured decision-making processes, and depend on human interpretation to bridge data with hopefully sound judgment.

To overcome this challenge, enterprises must rethink their AI workflows. Rather than AI serving as a co-pilot to human decision-makers, it should take the role of the pilot. In this model, humans shift from being the central drivers of decision-making to acting as data providers or experts who contribute insights only when the AI specifically requests them. The ideal scenario minimizes human intervention, enabling the AI to steer autonomously.

Extending the aviation analogy, this transition must be continuous. Instead of a static handover, the AI system should operate within a near real-time decision loop, constantly refining its approach based on new information and feedback. In doing so, the enterprise moves toward a state where human judgment is available on demand, but rarely required at the forefront.

A Real-World Example: Customer Service Chatbots

Let’s consider a simple but real-world scenario: a customer service chatbot. Imagine this bot has access to all relevant information—customer databases, Jira tickets, FAQs, and documented workflows. For simplicity, assume it achieves perfect accuracy in intent detection.

What failure modes remain?

1. The data is incomplete (e.g., it doesn’t know the answer).

2. The data is wrong (e.g., outdated FAQs or incorrect workflows).

In these scenarios, the fallback is often to engage a human. This is illustrative because it highlights what the AI system should ideally do: engage humans strategically when gaps arise.

Addressing Failure Scenarios

Two critical questions emerge:

1. What should happen next after a failure is detected and a human is engaged?

2. How could the failure have been avoided in the first place?

For the first question, the optimal response is to escalate the issue to a knowledgeable human (or multiple humans for high-stakes decisions), supported by the AI system in data lookup and verification. These escalated humans are likely not the same as the first-line responder—they must have the expertise to guide the system to the best resolution. Think of this as a "pager duty" for data management.

For the second question, prevention lies in robust simulations. For example, problem queries could be simulated using past customer interactions, exploring various branches of inquiry to proactively identify gaps in data or workflows.

This approach scales beyond customer service to more complex systems, such as financial modeling, supply chain management, and strategic decision-making.

Scaling the Solution

Inverting traditional workflows—placing AI in the pilot’s seat and using humans as expert data sources—can fundamentally reshape enterprise operations. When properly implemented, this approach not only taps into the best of human expertise on demand, but also ensures that AI systems maintain efficiency, consistency, and domain relevance over time. Yet, to realize these benefits, organizations must couple this human-in-the-loop paradigm with robust data-centric strategies, particularly when it comes to fine-tuning AI models. A carefully curated and differentiated dataset ensures that the AI’s internal parameters remain aligned with business goals and processes and reflective of the most reliable, high-quality information.

For this approach to succeed, enterprises should:

1. Automatically Query Human Input:
   Treat humans as dynamic, on-call domain experts who provide clarifications, judgments, and domain-specific insights exactly when the situation demands. This continuous, as-needed engagement ensures that fine-tuned models incorporate high-value human knowledge without depending too heavily on subjective inputs.

2. Simulate Task Inputs:
   Integrate continuous simulation runs. By proactively refining data quality and selection, the AI system stays prepared to handle new inputs effectively.

3. Continuously Update Data and Models
   Implement iterative pipelines that not only refine data selection, weighting, and filtering, but also continuously adjust the model’s fine-tuning parameters as it encounters new scenarios.

Enterprise AI systems can’t succeed if they’re treated as mere co-pilots. The future of AI in the enterprise requires rethinking workflows, prioritizing AI as the primary decision-maker, and leveraging humans as on-demand knowledge sources—brought into the loop only when their judgment or domain expertise is truly needed. This shift in perspective not only demands robust strategies for filtering, scoring, and fine-tuning proprietary data, but also calls for continuous refinement of how organizations manage, interpret, and integrate information into AI models.

By giving the AI system the reins, enterprises can better address the persistent issues of “dirty” data, the hidden complexities of human judgment, and the inherent challenges of operating at scale. The goal is not to diminish human input, but to transform it into a strategic resource that the AI can query as needed. This inversion—where humans assist AI, rather than the other way around—represents the logical next step in unlocking the full potential of AI within the future enterprise landscape.

Let’s face it—we can’t always control what we eat, especially if we want to participate in business and social life.

You eat at work, attend business or family functions, year-end parties, and let’s not even mention holidays and vacations. The energy balance equation can quickly get out of whack.

Let’s first address the topic everyone is talking about: GLP-1 receptor agonists. While I don’t have personal experience with them (don’t need it), I can see how they could be beneficial for many people. From what I understand, I don’t share many of the concerns about them. In biology, there’s no such thing as a "free lunch"—there’s always a risk/reward balance, and in the general case, being overweight and metabolically unhealthy presents a much higher risk.

GLP-1 agonists, such as semaglutide (sold under brand names like Ozempic and Wegovy), liraglutide (Saxenda), and tirzepatide (Mounjaro), have been used for years in the treatment of diabetes and off label in the body building community. These medications work by enhancing insulin secretion, slowing gastric emptying, and increasing satiety, leading to reduced food intake. The mechanism of action is well understood. However, the downsides are also known. One of the primary concerns is the loss of muscle mass along with fat, which can be a serious issue for sedentary individuals. So yes—if you’re considering using these medications, lift weights and eat plenty of protein.

There are some lesser-known issues, such as reduced heart rate variability (HRV), so I wouldn’t suggest casually using these drugs just to lose 10 pounds. But honestly, I see a lot of people who could have benefited from starting on them yesterday.

As for nutraceuticals, there are plenty of marketing claims about manipulating GLP-1 levels with probiotics, herbs, and other supplements. However, these claims are not supported by solid science. Mechanistically, to achieve the same effect as pharmaceutical GLP-1 agonists, you would need a 1,000-fold increase in the efficacy of these substances. So don’t bother.

The second approach is purely behavioral and has worked for me and many people I know—aligning your meal schedule with your circadian rhythm. This means eating three meals (breakfast, lunch, and dinner) at as consistent a time as possible each day, while absolutely avoiding any snacking between meals. Doing this helps prevent the constant need to eat by keeping your body in a more natural rhythm.

Regarding hunger between meals, there’s a remedy that can help (though, if you avoid snacking long enough, you will not need it). This involves using bitters, an ancient remedy believed to stimulate digestion and reduce appetite. Bitters work by activating bitter taste receptors in the mouth and gastrointestinal tract, which in turn stimulates the release of digestive enzymes and bile, potentially promoting a feeling of fullness or reducing cravings.

One specific supplement is Amarasate Extract, derived from New Zealand’s Gentian root. It contains bitter compounds that target receptors in the gut, signaling the brain to trigger satiety, which can help suppress appetite between meals. While these supplements aren’t highly effective for everyone, they can be a useful temporary hack until you get into the no-snacking habit.

Now, assuming you’ve got the basics under control but find yourself at a function with an overwhelming amount of tasty food (think authentic pasta dishes), self-control might not be enough—except for leaving early (which is often a good idea for other reasons).

First, front-loading with protein-rich foods when available (instead of carbs or alcohol) can help. This will increase satiety upfront, making you less likely to overeat.

Secondly, there are two pharmaceutical options you can consider:

1. Orlistat blocks pancreatic lipase, the enzyme necessary to digest fats. The over-the-counter dose is 60 mg, which is mildly effective, while the prescription dose of 120 mg is more effective, reducing fat calorie absorption by about 30%. However, a warning: overuse will reliably lead to gastrointestinal side effects, especially diarrhea.

2. Acarbose is a reversible alpha-glucosidase inhibitor that slows the breakdown of complex carbohydrates (such as pasta, rice, and bread) into simple sugars, delaying glucose absorption. Acarbose can lower postprandial blood glucose by about 20-40 mg/dL (closer to 20 mg/dL for me) per 25 mg dose, up to around 75 mg. Most of the calories from these carbs will eventually be absorbed, but some may pass into the large intestine, where they are fermented by gut bacteria. Beyond metabolic benefits, avoiding blood sugar spikes helps control hunger. Fun fact: Acarbose is only one of 3 drugs found to prolong lifespan in ITP (Interventions Testing Program) studies (the other two being rapamycin and SGLT2 inhibitors).

Both of these medications must be taken at the right time—specifically with meals. The official recommendation is to take them with the first bite of food, but I’ve personally found they work a little better if you take them a few bites into the meal.

When it comes to simple sugars, that’s the toughest challenge. Unfortunately, there’s no highly effective remedy for handling them (aside from SGLT2 inhibitors, which wouldn’t qualify as a party hack). One supplement with some evidence, though not strong, is Gymnema Sylvestre extract. This herb contains compounds known as gymnemic acids, which are thought to work by blocking the sugar receptors on your taste buds, reducing the sweetness sensation and potentially curbing sugar cravings. It may also slow the absorption of sugar in the intestines by interacting with glucose transporters. However, while Gymnema Sylvestre might help a little if taken about 30 minutes before a meal, especially with sugary foods, it’s far from a magic bullet for controlling simple sugars.

In conclusion, these strategies can help you shave off some extra calories and reduce hunger, allowing you to get through meals with minimal damage.

Hope this helps and love to hear your feedback,

Ruslan

Note: when I say something does or does not work for me, I rely on objective measurements, such as CGM in real-time, as well as calorie tracking (using Cronometer app), calorie expenditure (using Apple Watch), body composition (a scale as well as periodic DEXA scans).

What has remained elusive, however, is where differentiation will ultimately lie, specifically among startups.

In the interest of minimizing noise, I will omit opining on the most common themes that other people have been discussing at length (inference vs. training hardware, open-source vs. closed-source models, large vs. small models, various picks and shovels, and fine-tuning—though the latter remains an unsolved problem for application developers). All these areas have one thing in common: they require a lot of money and are thus mostly suitable for larger players.

The question is—where is, or is there, a differentiated opportunity? (And by differentiated, I mean outside of dumping a ton of money into a seed-stage company against a deck and a team—which can be differentiating on its own—or likely not.)

Let’s look at the basic structure of an LLM-first SaaS app. What does it need?

1. Access to a set of competent LLMs of different sizes at a reasonable cost and speed (many choices, nothing super differentiated).

2. A RAG system (i.e., pgvector)—not differentiated, especially with larger context windows, where the emphasis on retrieval accuracy is somewhat diminished.

3. An orchestration infrastructure: there’s basically a classic flow, such as intent detection, query rewriting, summarization, output checking, and correction. These frameworks will evolve, and there will be many options. In fact, with more and more LLM usage to write code itself, one could argue that frameworks like LangChain add more layers of complexity and problems than they solve—though I could be proven wrong. There could be new ways to think about frameworks in a world where most of the code would be generated.

4. A testing and observability infrastructure—definitely a major pain, but the problem area is obvious and many people are working on it. The question is whether it will spur s slew of new SaaS companies, or - considering immaturity of frameworks it will be more tightly coupled with service providers offering models and data services?

5. Coding tools (Copilot, Cursor, etc.)—again, quite obvious, and various tools will exist wrapping around ever-better models. The IDE becomes more of a very complex prompting interface and a feedback collection tool. There are several possibilities here:

   • A revolutionary new interface that we have not yet seen or thought of

   • A plethora of Cursor-like forks and VSCode plug-ins, though it’s difficult to see how they win, unless Microsoft simply yields. Cursor being superior to GitHub Copilot is mostly a function of Cursor RAG-ing your codebase, and GitHub being presumably more “privacy” conscious. A simple business decision by Kevin Scott can alter that equation overnight.

6. Differential fine-tuning and associated dataset management—no great solutions, but probably best addressed by model providers and companies like Scale.AI.

Alright. Some winners could emerge (especially around testing, and observability). It will likely converge into a few larger winners, most closely tied to model and data providers.

What are we overlooking? Can building an LLM wrapper be intrinsically differentiated? By intrinsically, I mean: is there an accumulation of leverage that creates a competitive moat over time? There’s always an opportunity to build a better product—better UX, clever influencer marketing, superior GTM—that leads to the acquisition of market share, and that can be differentiated, albeit hardly a sure thing.

There is likely one area that can be a source of leverage. We know proprietary data is that source in AI. But that’s too unstructured; to be differentiated, it needs to lead to a vastly superior outcome that is not obtainable by just using commonly available models.

So, what form is that, and how might it work?

When we look at a classic SaaS workflow (for example, responding to a customer service query), what happens is quite specific to each customer in two ways:

1. Prompts are likely different for each domain and further different for each customer.

2. Prompts involving function calling (i.e., opening a Jira ticket) are definitely different, especially if a custom integration is involved.

3. Workflow routing logic may be different (though this is technically outside LLM data).

4. Error checking and validation at the end of the action can likewise be very specific to a customer domain and environment.

Moreover, in other cases where user feedback is part of the loop, prompts may be dynamically updated (via LLM).

So, these prompts, in fact, constitute a customer-specific and user-specific dataset that grows over time, requires deep knowledge of customer workflows (and thus is not easily replicable), and grows over time.

Is this enough differentiation? Unclear—I think it depends on whether business workflows can converge and be serviced by a more intelligent model. However, to do so will require understanding these workflows first. While I think ultimately it will converge, there’s probably room on the way there.

Love to hear your thoughts,

Ruslan

Update (Mar, 2026)

Added:

• TUDCA: 1 service, 250mg AM/PM

  • TUDCA is here primarily as a liver and bile-flow support compound. Unlike many “liver support” botanicals, it is a bile acid derivative, so the rationale is more targeted: it helps make the bile acid pool more hydrophilic, may reduce stress on hepatocytes, and has a cleaner mechanistic case in the setting of a crowded stack plus mild liver-enzyme drift. I’m treating it as pragmatic insurance rather than a performance supplement — the goal is preserving liver resilience and bile handling, not expecting any noticeable day-to-day effect.

Removed:

• Acetyl L-Carnitine HCI: 1 serving, 1g

  • It does help transport fatty acids into mitochondria, acetyl-CoA group donor providing brain health benefits and good nootropic effects, and I did feel moderate benefits for the workouts. The downside - it feeds bacteria in the gut that produce TMAO. While TMAO impact is not completely settled, I am removing ALCAR on risk/reward basis, especially considering absorption problems with oral forms in general.

• Cordyceps: 1 serving, 2g

  • Preliminary research suggested that Cordyceps may have positive effects on telomere length. Subjectively I did not feel any effect and upon further examination telomere length rationale is quite weak. Removing to simplify the stack.

Removed:

• EGCG 1/2 serving, 1 cap, 200mg 2x/day

  • Originally the thesis here was colorectal risk mitigation (there is mechanistic plausibility + some human data in the adenoma space), but on the latest labs I saw a mild upward drift in liver enzymes. Green tea extracts are one of the more common “usually fine, but occasionally not” botanicals from a liver standpoint — and when you’re monitoring LFTs, anything with even a small hepatotoxicity signal is a poor fit. Net: risk/reward no longer pencils out for me right now, so it’s out until LFTs normalize and a future re-challenge (if any) can be done cleanly.

• AC-11 1cap 350mg into the morning shake

  • This was a pure experiment around the “DNA repair / resilience” claims. After a reasonable run, the subjective benefit was barely detectable and I couldn’t find anything objective to justify keeping it in. Given how crowded the stack already is, anything that isn’t clearly pulling its weight gets cut.

• Gotu Kola extract: 1/2 serving, 1 cap, 120mg

  • I like Gotu Kola for microcirculation / skin-collagen support, but similarly to EGCG it’s a botanical with rare (but real) hepatotoxicity case reports. With LFTs already trending the wrong way, this becomes an obvious “first things to pull” candidate. Removed for now.

Added:

• Urolithin A, 1/2 service, 1 cap, 1000mg, PM

  • Urolithin A is here for mitochondrial “quality control” via mitophagy — i.e., preferential cleanup of dysfunctional mitochondria rather than just suppressing ROS. Another reason I like it: humans vary a lot in how well they can generate urolithins from food (microbiome-dependent), so supplementing can bypass that variability. The human RCT data isn’t perfect, but it’s stronger than most “mitochondrial” supplements, with safety/tolerability plus measurable signals on muscle endurance / mitochondrial health markers.

• PQQ: 1 cap, 20mg (AM)

  • PQQ is a redox-active compound with a plausible role in mitochondrial biogenesis / cellular energy metabolism, and there are a few small human studies with signals on inflammation markers and cognitive endpoints — nothing definitive. I previously ran it and couldn’t find a clean personal signal, so conviction remains low. I’m re-running it only because it pairs conceptually with Urolithin A (different mechanism, same “mitochondrial cleanup + support” direction) and it’s easy to discontinue if it stays silent.

• Colostrum 1 scoop, 1g, morning shake

  • Colostrum is a “gut insurance” lever for me: bovine colostrum concentrates immunoglobulins (IgG), lactoferrin, and other bioactives that support barrier integrity and innate immune function. The best human data I’ve seen is in athletes / high training stress contexts, where colostrum has been associated with improved gut permeability markers and fewer URTI-type issues. I’m using a conservative dose (1g/day) and treating it as supportive — not magic. Avoid if dairy allergy is a concern.

Updated:

• Bacopa Monirelli (Synapsa): 1 serving, 320mg

  • Formulation changed to Cognance 1 serving, 100mg with rationale being a better overall profile with no potential sedation effects.

Update (Oct, 2025)

• Replaced Reishi mushroom powder with Turkey Tail mushroom powder: 1 serving, 1g (2 days on, 1 day off - non overlapping with Lion’s Mane). Reasons:

  • Safety/monitoring—Reishi has rare but documented hepatotoxicity case reports and inclusion in LiverTox, which matters if you’re watching LFTs; Turkey Tail has a long clinical track record as an adjuvant (PSK) with generally favorable tolerability.

  • Evidence fit—Turkey Tail’s PSK/PSP have been studied extensively as immune modulators (including RCTs), with signals on NK-cell activity and broader immune function, making it a reasonable like-for-like immunologic substitute

  • Potential 5-AR inhibition: There’s some weak evidence that Reishi may have an anti-androgenic potential, which we obviously don’t want

• Added another Creatine: 1 serving, 5g to the morning shake for 10g total (between pre-workout and the morning shake). New research strongly suggest cognitive benefits (especially when short on sleep) from this dosing and subjectively I feel a noticeable boost and no afternoon slump at all.

Update (Aug, 2025)

Added:

• Tongat Ali was replaced Eurycomax and correspondingly 2.5mg of Pregnenolone was removed. In total between Cistamax, Eurycomax and direct supplementation DHEA and Pregnenolone dosages stayed at 5mg each. So far appears to be a much smoother stack.

• Maca extract powder was added to the morning shake at 200mg. See notes.

• Gotu Kola was added into the morning shake along with the evening dose.

• EGCG was added into the morning shake along with the evening dose. See notes.

• Stinging Nettle Root Root extract was added into the morning shake along with the evening dose.

• NMN/NR stack was restructured and replaced with NR (Tru Niagen) plus Pterostilbene+Quercetin. See detailed discussion.

• AC-11 was added experimentally, 1cap 350mg into the morning shake. So far seem to generate a slight mental kick. Data-wise not yet convinced.

• Creatine was moved from morning shake to pre-workout. Seemed to make a significant difference, probably due to transient DHT elevation.

• Rosuvastatin (Crestor) along with Geranylgeraniol were moved from AM to PM to avoid (theoretical) transporter conflicts with other supplements.

• H2 Molecular Hydrogen was added along with the morning supplements. See notes.

Removed:

• Gaia Herbs Adrenal Health Daily - I took this for years; it made my original list because it seemed helpful during a heavy-stress period. That said, I’ve always been skeptical of “adrenal support” blends—sensible ingredients, but usually well below clinically studied doses. After multiple on/off cycles, I’m convinced it isn’t doing anything meaningful (and at worst may slightly lower morning cortisol from the small amount of ashwagandha).

Update (Sep, 2024):

Added:

• Spermidine (see AM morning shake section)

• Magnesium Glycinate, 200mg in the evening replacing Magnesium complex

Removed:

1. C60 (in olive oil): 1 tsp

   The premise: an interesting compound due to it’s direct and unique anti-oxidant action that doesn’t blunt effects of exercise.

   It was an experiment and thus far I have not found neither subjective nor objective evidence of it doing anything (perhaps it was a problem with a specific brand).

2. PQQ: 1 cap, 20mg

   The premise: research around mitochondrial support effects is quite solid. Quantitatively or subjectively I couldn’t see or feel anything.

3. Probiotics

   After experimenting with several over the years, I found them to be useful for a specific purpose, but not as part of a maintenance routine.

Everyone is asking what supplements I take. I am going to share full list upfront and then we are going have a discussion.

Several disclaimers:

• This list is highly personalized and is periodically revised based on quantitative testing, research updates, and subjective evaluation. What you see here is a snapshot as of today.

• None of this is a medical advice. Please, do not apply this list to yourself without proper medical guidance.

• It's crucial to remember that, from a scientific perspective, supplements (and even diet) are not as significant as one might think compared to exercise. Nutrition and supplement studies are typically of low quality and should be viewed with skepticism. They are most often based on epidemiology, which is unreliable due to confounding factors, biases, and difficulty in establishing causality. Although Mendelian randomization trials are more robust in inferring causality, they are limited in number due to costs and incentives. When they are done - these trials are often underpowered, too short, and tend to focus on populations that may not be relevant to our purposes.

• Therefore, the totality of data, including observational data from various traditions, along with personal biomarkers, functional fitness metrics, and subjective evaluations, must all be considered.

• Given the difficulty of evaluating efficacy, why do I pursue this? Partially, it's for the fun of biohacking.

• The main goals for me are health span and performance (not longevity by itself - who wants to live longer without being able to do things anyway).

Here’s how to read the list:

• Supplement: (including the specific brand I use and dosages; note that I have no affiliation with any of the companies mentioned).

• Commentary: I’ll provide brief commentary without references (for the sake of my time). Accuracy is not guaranteed. Feel free to discuss it further with ChatGPT.

• Risk: low/medium/high (I don’t use anything I consider high risk). No supplement is zero risk as unknown effects may exist, and there could be discrepancies versus the label due to manufacturing or quality control issues.

• Personal outcome: none/minor/notable/significant - a subjective evaluation of the benefit based on an aggregate of biomarker, functional testing, and subjective feelings of well-being.

• Conviction: low/medium/high - my current level of conviction in the supplement's efficacy based on the aggregate of data, research and personal outcome.

Let’s get right to it.

AM - Pre-workout

As you know from my earlier post - I workout first thing in the morning and that drives some of the logic here (if I was to work out in the afternoon or the evening - the supplementation would be different)

The following supplements are mixed in as powders into a pre-workout drink:

Essential Amino Acids (EAAs): 1 serving, 11g

As I work out in the morning and we know that in a hypo-caloric state the body can break down muscle for energy, having circulating amino acids (in addition to the stimulus from exercise) helps preserve muscle mass. Essential Amino Acids (EAAs) are beneficial because they are already in their simplest form and are readily available for muscle protein synthesis. This makes them easier for the body to use immediately compared to whole proteins, which need to be broken down first. Additionally, EAAs are easier on the digestive system.

Risk: low

Personal outcome: significant

Conviction: high

Legion Pulse Pre-Workout drink: 1/2 serving, 11.75g

This product serves as both a nootropic supplement and a pre-workout aid. It’s a well-designed product with no filler or questionable ingredients. The main components are: a moderate dose of caffeine for increased energy and focus, L-Citrulline for nitric oxide enhancement and improved blood flow, Betaine/TMG which helps control homocysteine levels (this ingredient combines nicely with other supplements, such as NAD precursors) and has several performance benefits, L-Theanine for its calming and focus-enhancing effects, Alpha-GPC as an effective acetylcholine precursor for cognitive enhancement, and electrolytes (sodium and potassium) to support hydration and muscle function.

Risk: low

Personal outcome: significant

Conviction: high

Taurine: 1 serving, 2g

The research on taurine is impressive on many levels, demonstrating benefits for cardiovascular health and muscle function. However, I am not sure it’s doing anything noticeable for me personally. Taurine supplementation might be more important for people on a vegetarian or vegan diet, as they may have lower taurine levels due to the absence of taurine-rich animal products in their diet.

Risk: low

Personal outcome: none

Conviction: low

Collagen: 1 serving, 10.29g

Collagen helps complement the amino acid profile provided by EAAs, offering specific amino acids like glycine, proline, and hydroxyproline. Research suggests that taking collagen prior to a workout, assuming adequate exercise stimulus, can support connective tissue and joint health, with some evidence also indicating benefits for bone health. This particular product uses special formulation of collagen and has additional ingredients such as Hyaluronic Acid, ch-OSA, and Buffered Vitamin C, which are known for their synergistic benefits for joint health.

A side note: excess collagen, due to conversion of hydroxyproline into oxalates. Between this dose and the morning shake it comes down to 20g / day for me, which may be close to an upper safe dose.

Risk: moderate

Personal outcome: notable

Conviction: high

N-Acetyl L-Tyrosine (occasionally): 1 serving, 0.4g

N-Acetyl L-Tyrosine (NALT) is a precursor to neurotransmitters such as dopamine, norepinephrine, and epinephrine, as well as thyroid hormones like thyroxine (T4) and triiodothyronine (T3),, which can enhance mental focus and cognitive performance. I take it occasionally for an extra kick during workouts, as it helps improve alertness and mental clarity, contributing to a more energized workout experience.

Risk: low

Personal outcome: notable

Conviction: moderate

The following supplements are taken separately as capsules along with the pre-workout drink at the same time:

CistaMax (5 days on, 2 days off, 2 weeks washout every 10 weeks): 1 serving, 1 cap

This is an amazing combo and you have to admire the thinking that went into designing it. It would take a couple of pages to dissect it - so for the sake of time do your own research here.

Risk: moderate

Personal outcome: significant

Conviction: high

Eurycomax (5 days on, 2 days off, 2 weeks washout every 10 weeks): 1 serving, 2 caps

Eurycomax is the new great combo based around Tongat Ali with additional ingredients, and it seems to avoid some of the concerns with pure Tongat by better balancing estrogen suppression. A reminder - anytime you are tinkering with hormones even a little, quantitative testing is a must to ensure safety and efficacy.

Risk: moderate

Personal outcome: significant

Conviction: high

DHEA: 1/2 serving, 1/2 tab, 2.5mg (5 days on, 2 days off)

At very low doses - such in in my case for a total of 5mg of DHEA and 5mg or Pregnenolone between DHEA tablet, Eurycomax and Cystamax this helps nudge, especially as we age the process of steroidogenesis in the right direction, towards testosterone synthesis without triggering negative effects and feedback loops.

Risk: moderate

Personal outcome: significant

Conviction: high

Creatine: 1 serving, 5g

The benefits of creatine are well known - both for muscle endurance and brain (and even systemically).

There’s a plausible risk of DHT elevation (and resulting hair loss). The one frequently quoted study was not replicated and there’re other issues with it (however, anecdotally there are a lot of bold body builders). Either way keeping an eye on DHT levels is recommended if hair loss is a concern.

Secondarily, creatine supplementation will elevate blood creatinine levels that will show up on a standard metabolic panel test (such as CMP). This is not a concern - if the cause is Creatine supplementation. However tell your doctor, so a more accurate biomarker can be used to assess kidney health (such as Cystatin C).

Finally - note that creatinine as well as liver enzymes (ALT most notably) can also be elevated due to normal muscle breakdown as a result of a strength training session, so likewise tell your doctor or use a wash out period (72 hours - I am not doing it).

Note: when you severely underslept for whatever reason, additional 5mg of Creatine later in the day (I’d just add that extra dose into the morning shake) could be quite helpful as a temporary fix.

Risk: low

Personal outcome: significant

Conviction: high

AM - Breakfast (Post workout)

These are taken in conjunction with my morning shake and whenever possible I use powders (instead of capsules, to avoid filler ingredients and flow agents) and capsules (whenever a powder form is not available) are broken up and put into the shake. Using powders is also more cost effective.

Core Morning Shake recipe

Whey Protein: 25g

Collagen Protein: 9g

Fiber Powder (most days, but sometimes I skip adding it when I want to give my gut a break from extra fiber)

Wild blueberry or elderberry powder: 5g (alternating)

Pomegranate powder: 1 tbs

Tart cherry powder: 4.8g (among many other benefits this helps to keep uric acid at low levels).

Olive oil, 2 tsps (to make sure there’s a little bit of fat to help with absorption of fat soluble vitamins).

Some sort of fruit from whatever is around, could fresh or be frozen: banana, a cup of strawberries, raspberries, an apple, 2 peaches, 3 apricots, etc.

Supplements that are mixed into the shake

O.N.E. multivitamin: 1 serving, 1 cap

Think of it as an insurance policy, although given my genetics - methylated B vitamins are great. There’s no perfect multi-vitamin and it’s a compromise for convenience.

Risk: low

Personal outcome: minor

Conviction: high

Magnesium complex: 1/2 serving, 1 cap, 120mg

The benefits are well documented, especially considering that it is nearly impossible to get enough magnesium through the regular modern diet (with all the soil depletion).

Risk: low

Personal outcome: minor

Conviction: high

Glucosamin HCI: 1 serving, 1g

Decent research for joint (formation and repair of cartilage, synovial fluid production) and even brain health.

Risk: low

Personal outcome: minor

Conviction: moderate

Colostrum 1 scoop, 1g, morning shake

Colostrum is a “gut insurance” lever for me: bovine colostrum concentrates immunoglobulins (IgG), lactoferrin, and other bioactives that may support barrier integrity and innate immune function. The best human data I’ve seen is in athletes / high training stress contexts, where colostrum has been associated with improved gut permeability markers and fewer URTI-type issues. I’m using a conservative dose (1g/day) and treating it as supportive — not magic.

Risk: low

Personal outcome: minor

Conviction: moderate

Stinging Nettle Root Extract, 1/2 serving, 1 cap, 250mg

Mechanism of action is anti-androgen activity specific to prostate, thus not affecting androgens systemically, which is quite nice. The outcomes are supported by solid data, including human trials.

Risk: low

Personal outcome: significant

Conviction: high

PQQ: 1 cap, 20mg

PQQ is a redox-active compound with a plausible role in mitochondrial biogenesis / cellular energy metabolism, and there are a few small human studies with signals on inflammation markers and cognitive endpoints — nothing definitive. I previously ran it and couldn’t find a clean personal signal, so conviction remains low. I’m re-running it only because it pairs conceptually with Urolithin A (different mechanism, same “mitochondrial cleanup + support” direction) and it’s easy to discontinue if it stays silent.

Risk: low

Personal outcome: none

Conviction: low

Bacopa Monirelli (Cognance): 1 serving, 100mg

Bacopa is a long-running cognitive “insurance” herb with human trial data suggesting benefits for memory/processing after weeks of consistent use (with GI side effects being the most common downside). The trade-off with traditional bacopa extracts is that some people feel slightly sedated or “flat.” Cognance is a newer bacopa extract with a different standardization profile, and the bet here is keeping the brain-support upside while avoiding the sedation tax.

Risk: low

Personal outcome: minor

Conviction: moderate

Maca Extract Powder (5% macamides): 1 serving, 125mg

An interesting compound that inhibits FAAH (the enzyme that breaks down anandamide), which can raise endocannabinoid tone. The result is a noticeable mood and well being elevation. The safety record is excellent and it appears not to affect hormones or major neurotransmitters.

Risk: low

Personal outcome: notable

Conviction: moderate

Lion’s Mane: 1 serving, 1g, 1 day on, 2 days off

For brain benefits as it is known to increase both BDNF (Brain-Derived Neurotrophic Factor)) and especially NGF (Nerve Growth Factor).

Risk: low

Personal outcome: minor

Conviction: moderate

Turkey Tail mushroom powder: 1 serving, 1g (2 days on, 1 day off - non overlapping with Lion’s Mane)

The idea is to boost NK-cell activity as a preventative. Turkey Tail —notably its PSK/PSP fractions and mycelium—has human data showing increased NK-cell tumoricidal activity and higher circulating NK cells vs. control: a phase-I study in breast-cancer survivors reported improved NK function and lymphocyte counts; a randomized double-blind trial linked rises in the NK-activation marker CD69 to functional gains; and oncology RCTs using PSK showed peripheral NK-cell increases compared with control.

Note: if you have any kind of autoimmunity, I would avoid.

Risk: low

Personal outcome: minor

Conviction: moderate

Inositol: 1 serving, 1g

Supports healthy thyroid function and helps keeps TSH levels in the optimal range.

Risk: low

Personal outcome:: notable

Conviction: high

Milk Thisle, 1 serving, 100mg

Milk thistle is well-researched for its liver support properties, primarily due to its active compound, silymarin. Silymarin has antioxidant, anti-inflammatory, and antifibrotic effects, which help protect liver cells from damage, support liver regeneration, and improve liver function. Probably a good insurance with all the other supplements I am taking 🙂.

While research supports these benefits, it hasn’t been enough time to ascertain the results for me personally.

Risk: low

Personal outcome: none

Conviction: low

Spermidine, 1 service, 2 caps, 13mg equivalent

Spermidine induces autophagy by inhibiting the activity of key enzymes involved in acetylation, such as histone acetyltransferases. This inhibition leads to the deacetylation of autophagy-related genes, which promotes the formation of autophagosomes—vesicles that engulf and degrade damaged proteins, organelles, and cellular debris.

Risk: low

Personal outcome: none

Conviction: moderate

TruNiagen NR: 1 serving, 1 cap, 300mg, combined with Quercetin + Pterostilbene, 1 serving, 2 caps, 500mg Quercetin, 50m of Pterosilbene)

This deserves a bit of discussion. The whole idea of using NAD+ precursors came out of research by David Sinclair. We know NAD+ decreases as we age and it is important with 1000s different things, most interestingly with Sirtuin activation (Resveratrol or similar compounds, such as Pterostilbene).

However there’re many issues with it:

1. No positive effects have been observed in humans thus far (except for one study on cognitive health with NR)

2. Both NR and Resveratrol failed ITP studies (which thus far is a gold standard for longevity research).

3. The original Resveratrol study has been thoroughly discredited due to study design (in fact it turned out to be so bad, people wonder how it (and it’s authors) got so much attention in the first place),

4. There is a rodent study showing cancer growth acceleration effects from NR (for pre-existing cancers - mechanistically this makes sense as NAD+ is quickly depleted by hungry cancer cells, and replenishing NAD+ will only accelerate that process)

5. There is a concern of up-regulating CD38, although in moderate doses this should not be a concern (there’s yet to be determined U-shape curve here that may depend on many variables). This could potentially be mitigated by Quercetin.

6. Bio-availability of Resveratrol is low (I am using Pterostilbene instead for that reason, although it’s not clear that it is doing anything either).

7. In addition any of these precursors need to be supplemented with TMG (in my case there’s plenty in Legion pre-workout drink) to prevent elevation of homocysteine due to back conversion to nicotinamide.

That said - mechanistic theory around how all this could work for longevity is quite compelling and it is possible that it would take considerable time for it to work.

Subjective effects for me in terms of feeling more energetic, however the question is whether supplementing with plain old nicotinamide would accomplish the same outcome (including NAD+ support) for a fraction of the cost.

Finally - there’s still a serious, unresolved conundrum here. NAD+ enhances cellular energy by participating in mitochondrial redox reactions, boosting ATP synthesis (hence feeling energetic). It is also essential for sirtuin activation, which signals autophagy and repair—processes that act as evolutionary sensors for low nutrient levels.

However, consuming a lot of protein, necessary for maintaining muscle mass, stimulates the mTOR pathway, contradicting these aims. The mTOR pathway promotes cell growth and inhibits autophagy, counteracting the benefits. An alternative approach involving cycling and agents like Rapamycin might be better, but the exact protocols and pros and cons are unclear. Most importantly, I would have no idea how to reconcile it with my everyday workout routine.

Risk: moderate

Personal outcome:: notable

Conviction: low

Supplements taken along with the shake / breakfast

These are supplements that are not (or cannot be) available in a powder form or breakable capsules.

EPA/DHA: 1/2 serving, 1 cap

Not much to opine on, the benefits of EPA/DHA are well researched. I keep my omega index >8 (8.94% as of last test) on OmegaQuant test (your dose may vary, so test it).

Risk: low

Personal outcome: minor

Conviction: high

Vitamin K1/MK-4/MK-9: 1 serving, 1 cap

A must considering supplementation with Vitamin D (O.N.E. multivitamin has 2000 IU), plus other vascular and bone health benefits.

Risk: low

Personal outcome: none (as far as subjective feeling, calcium score continues to stay at 0 and bone density on DEXA went up - so that’s be pretty good)

Conviction: high

COQ10: 1 serving, 1 cap, 100mg

The idea here is to counteract effects of a statin that whacks HMG-CoA enzyme and decreases COQ10 levels as a result. While studies are conflicted, the subjective feeling is noticeable for me.

Risk: low

Personal outcome:: notable

Conviction: high

TUDCA: 1 service, 250mg

TUDCA is here primarily as a liver and bile-flow support compound. Unlike many “liver support” botanicals, it is a bile acid derivative, so the rationale is more targeted: it helps make the bile acid pool more hydrophilic, may reduce stress on hepatocytes, and has a cleaner mechanistic case in the setting of a crowded stack plus mild liver-enzyme drift. I’m treating it as pragmatic insurance rather than a performance supplement — the goal is preserving liver resilience and bile handling, not expecting any noticeable day-to-day effect.

Risk: low

Personal outcome:: none

Conviction: high

Smart PS™ Phosphatidylserine: 1 serving, 1 cap

This is a blend of phosphatidylserine, phosphatidylcholine, and phosphatidylethanolamine and supports brain health by providing essential phospholipids that contribute to cognitive function, memory, and overall neural health by playing a key role in cell membrane integrity and the formation of synaptic vesicles.

Risk: low

Personal outcome:: minor

Conviction: high

Aged Garlic Extract: 1/2 serving, 1 cap, 300mg

This is to mitigate the potential increase in TMAO levels caused by ALCAR and choline precursors, as elevated TMAO has been associated with cardiovascular risk. While the link between TMAO and ASCVD (Atherosclerotic Cardiovascular Disease) is not definitively proven (as otherwise people who eat a lot of fish would all die from heart attacks - which is obviously not the case), there is enough evidence to warrant some precaution. AGE has additional benefits, such as mild cholesterol-lowering effects, but those are not the primary reasons for taking it in this case. Note that garlic is a FODMAP and may cause digestive issues for some people, especially those with SIBO.

Risk: low (see above)

Personal outcome: none

Conviction: low

H2 Molecular Hydrogen: 1 serving, 1 tablet (80mg magnesium, 8ppm), dissolved in water when taking other supplements.

There is a significant body of research suggesting that H2 is a selective antioxidant neutralizing mostly the harsh stuff (•OH, ONOO⁻) while sparing signaling ROS (e.g., H₂O₂) that drive exercise adaptations.

Risk: low

Personal outcome: none

Conviction: low

Prescription medications

Goes without saying that these always must be discussed with and prescribed by your doctor.

Rosuvastatin (Crestor): 5mg (PM)

While there’s a lot of controversy around the use of statins - I am quite convinced based on available research. ASCVD progression is a stochastic process and keeping APO-B concentrations low is, in my opinion very much worth it.

That said - statins are not perfect drugs with a lot of off target effects. First, they work by suppressing HMG-CoA cascade, that causes all kinds of problems. Secondly it seems there’s causal evidence of increase in insulin resistance overtime. On top of that, there’re negative effects on liver (observed by modest elevation of liver enzymes and despite unclear clinical significance - this is still not cool).

That said, for me Rosuvastatin is still the best (of imperfect) choices. First - it is the only effective hydrophilic statin that (unlike lipophilic statins, such as Atorvastatin (Lipitor) doesn’t massively diffuse into tissues or crosses the blood-brain barrier (thus reducing potential side effects, such muscle soreness).

Risk: moderate

Personal outcome: notable (as measured by calcium score staying at zero)

Conviction: high

Tadalafil (Cialis): 5mg (AM)

While developed as an ED drug, I take it for it’s off target systemic effects on improving the blood flow. As we know - most ills stem from poor blood flow as we age. Improved circulation also enhances workout performance and supports overall cardiovascular health, contributing to smoother functioning of many bodily systems. Tadalafil also slightly lowers blood pressure, helping to maintain it within the optimal range.

Risk: low

Personal outcome:: significant

Conviction: high

Minoxidil (Loniten): 2.5 mg (PM)

I am using it as a preventative for hair loss at low dose (it is an old, repurposed blood pressure medication). It doesn’t seem to affect the blood pressure much for me, if anything it may be lowers it by a few points, which is a nice bonus. Otherwise no noticeable side effects.

Coffee

The discussion would not be complete without coffee. Coffee is one of the most widely used drugs in the world. 67% of Americans drink coffee (that’s why I suppose it just got removed from the CPI by the BLS as the price of coffee has been going up).

I take my coffee black (Americano) with no milk or sugar of course. I do add 1 tsp of C8 MCT oil into my morning coffee.

On most days that be just one mug, but sometimes I also get the second cup around lunchtime. More than that starts adversely affecting my sleep quality - so if I must, I switch to decaf.

PM (with dinner)

EPA/DHA: 1/2 serving, 1 cap

The second dose as in AM.

Magnesium glycinate: 1 serving, 1 cap, 200mg

Seem to be more effective than than standard magnesium complex and has a notable calming effect for sleep.

Risk: low

Personal outcome: significant

Conviction: high

Magnesium L-Threonate: 2/3 serving, 2 caps, 96mg

Brain health benefits and a minor calming effect for sleep.

Risk: low

Personal outcome: minor

Conviction: low

COQ10: 1 serving, 1 cap, 100mg

The second dose as in AM.

TUDCA: 1 service, 250mg

The second dose as in AM.

BroccoMax: 1 serving, 2 caps

The research is decent, especially around colon cancer prevention effects. However I can’t quantitatively put a handle on it for me personally thus far.

Risk: low

Personal outcome:: none

Conviction: low

Urolithin A, 1/2 service, 1 cap, 1000mg, PM

Urolithin A is here for mitochondrial “quality control” via mitophagy — i.e., preferential cleanup of dysfunctional mitochondria rather than just suppressing ROS. Another reason I like it: humans vary a lot in how well they can generate urolithins from food (microbiome-dependent), so supplementing can bypass that variability. The human RCT data isn’t perfect, but it’s stronger than most “mitochondrial” supplements, with safety/tolerability plus measurable signals on muscle endurance / mitochondrial health markers.

Risk: low

Personal outcome: none

Conviction: moderate

Stinging Nettle Root Extract, 1/2 serving, 1 cap, 250mg

The second dose as in AM.

Risk: low

Personal outcome: significant

Conviction: high

Aged Garlic Extract: 1/2 serving, 1 cap, 300mg

The second dose as in AM.

Risk: low

Personal outcome: none

Conviction: low

Geranylgeraniol: 1 serving, 1 cap

A fairly new compound that also counteracts negative effects of statins, by a different mechanism.

Geranylgeraniol (GGOH) is a critical intermediate in the mevalonate pathway, downstream of HMG-CoA reductase and it is necessary for the prenylation of small GTP-binding proteins. Prenylation is a post-translational modification that allows these proteins to anchor to cell membranes and function properly.

By supplementing with GGOH, the normal function of these prenylated proteins can be restored. Subjectively for me it appears to be even more efficacious than COQ10 (although I would keep both as mechanisms and effects are different).

Risk: low

Personal outcome: notable

Conviction: high

Discussion

So, that's a lot of supplements. The question is: can you achieve the same results with just a good diet? Probably not.

Even if you source high-quality ingredients and are prepared to spend an inordinate amount of time cooking everything perfectly, it's unlikely you'll achieve all the effects and benefits tailored to your genetics, personal health circumstances, and performance goals without some scientific enhancement.

The second question: can you avoid supplements altogether? Of course, you can. The human body is very resilient and can tolerate suboptimal conditions for a while. However, if performance optimization is your goal, then supplementation should be considered.

Another point: ingredients in food are presumably in more natural ratios than in a synthetically constructed supplement regimen. True. However, our body is highly adaptable and can handle a lot of variation. Besides, common processed foods like french fries and soda are far from natural or balanced.

Another concern is supplement quality, fillers, and labeling. This is valid. Fillers are problematic, which is why I opt for powders, choose the cleanest possible options, and stick with reputable brands. Risks, such as heavy metal contamination, do exist, but they are manageable if you monitor important biomarkers regularly. On the flip side - common food products are hardly immune from this problem, from Glyphosate, micro-plastics, heavy metals and other types of contaminants.

Does it take a lot of work? Some, but not a lot, as I've fine-tuned my routine over the years. I also batch my shakes, preparing and mixing them on the weekend for the week, so the actual breakfast prep takes very little time.

Hope this helps - in whatever way it does 🙂

What prompted me to opine here was an accidental feature we developed at Jelled.AI that sorts communications that you don’t need to pay attention to out. Looking at the results of it - it got me thinking. I will explain.

But first - there is no surprise the efficacy of cold outreach emails has been declining (despite all the hacks - that largely do not work) and probably reached the point (with the introduction of AI tools into sales workflows) where the cost to send them is near zero, but the efficacy is an asymptote of zero. In fact I would argue there’s a high probability of a net negative return as receiving cold emails could drain whatever good will the customer could have had before opening them.

My personal routine handling inbound sales outreach was as follows:

1. I never respond to cold sales outreach, except if it’s from founders

2. I will mark repeated sales outreach email as spam (although that doesn’t seem to help due to various email distribution tricks people are using) and will block the sender.

Nonetheless - that’s still annoying.

So - with the new feature, Jelled.ai automatically detects inbound sales emails (so far with 100% accuracy) and sorts them out into a separate folder (the AI engine itself keeps the content if you ever need to do a research on it in the future). As a result - my inbox is super clean and I no longer get annoyed by the all the inbound.

However - this brings up several interesting observations. While using LLMs to generate emails is practically free (comparing to other methods involving humans) - getting rid of these emails is also free. Therefor the usefulness of the cold outbound channel is NIL and the only people making money here are from OpenAI.

The voice channel was already useless (I never ever pick up the phone in the first place if you are not in my address book). Text will largely meet similar fate (including mentions).

So, if cold outbound is of no value - that means that the value of SDRs is just an expense (the introduction research can be done by AI agents, while the introductions will still need to be done through the influencer network).

What does this do? Does It invert the SaaS sales model as it empowers the buyer to run a competitive bidding process through AI - which is already aware of company plans, budgets, timelines, etc.?

This, being on top of other AI advances, brings into question the need for CRM systems—which really have nothing to do with customer relationship management but are designed to manage the salesforce. Humans are forgetful, unorganized, need complex compensation plans, and are generally flawed. AI-first designed systems will obviously not have any of those problems. Additionally, as we have fewer humans, we will need fewer seats—there goes your pricing model as well.

Are we going to see an upheaval in the world of Salesforce? Does it apply to other professionals (in marketing for example)?

Something possibly to keep an eye on in the near future.

Thoughts welcome!

A quick evening note here—without going too deep or referencing sources and benchmarks—on the 3 claims that I am personally skeptical about.

Open source models will catch up with closed source models

The argument goes something like this: "The web is finite, therefore all data is/will ultimately be available for training, and what is not available (proprietary data) will remain a small fraction and thus of little impact. From there, it follows that if all models are trained on the same data, the performance will inevitably converge, and therefore there is not much value add in proprietary models."

The thing is, even if we assume that most relevant data is freely available (various legal issues aside), it takes a lot of resources to train and update the base model and even more resources to instruct it to make it useful (considering all the infrastructure setup and humans involved). While off-the-shelf models like LlamaN… may work in some contexts, it is unlikely to form a foundation for a true competitive advantage.

What can alter this dynamic? Perhaps new architectures and approaches to training and fine-tuning, making the process a lot less resource and cost intensive.

LLM utility is limited to text generation

(or image generation)

From a first principles standpoint, this is true. We see that auto-regressive generation (LLMs) is "an exponentially divergent diffusion process, hence not controllable."

However, a combination of LLM with pure logic software may be able to yield good planning/reasoning outcomes, albeit not yet broadly generalizable.

For example, having an LLM generate code, attempt to run/fix that code, and later evaluate the output demonstrates this is feasible. In addition, this limitation is so well understood and so many people are working on solving it that inevitably—scalable solutions will come, or at least it’s not unreasonable to bet on it.

LLMs are too slow for real-time user workflows

This is true on the face of it, and a massive improvement is unlikely in the medium term.

However,

there are a lot of (if not the majority of) workflows, especially enterprise workflows, that are not real-time and do not need to be real-time - communication, document generation, analytics, and many others). So, not only can we take our sweet time, but we can also execute very complex, multi-step LLM workflows without issues (except for cost). In fact, the cost right now is a much bigger problem.

There are also a ton of performance tricks one can play (from caching, progressive enhancement, different models for different tasks) to make the system look a lot more performant than it really is.

Happy Sunday and to the productive Monday,

Ruslan

These days, everyone is a Nostradamus when it comes to AI, and I am going to try to avoid direct predictions. The future is always uncertain, yet some clusters of opportunity are still visible.

To refresh the basics, the main breakthroughs so far have come from:

1. Compute (training/inference) and the ability to store and handle large amounts of data

2. Development of Word2Vec and subsequent advances in efficiently learning word embeddings

3. Transformer architecture that dispensed with the sequential processing of RNN-type architectures, enabling the practical training of large models

The main unknown factor was when exactly the compute and the data would lead to breakthroughs. Just like with CNNs for vision, there turned out to be a threshold past which things just started to work.

Again, it's important to remember that all an LLM does is predict the next token. So, how is it exactly useful?

Well - isn't that what people do? That's why hallucination is not a bug, but the key feature. One could conflate the LLM temperature setting (a hyperparameter used to tweak the probability distribution for selecting the next word) with the number of drinks at a party.

It has also been fascinating to observe the evolution of open-source LLMs and various claims of models of GPT 3.x quality (interestingly, no one so far has reached GPT-4 quality even according to benchmarks - and one should be very skeptical of benchmarks at this stage). Why is that?

Well - let's look deeper at what influences LLM quality:

1. The dataset to train the base model: if your base dataset contains clean, large, high-quality data - such as well-written books, legal libraries, scientific articles, as opposed to data scraped from the web - your next-word predictions will be more aligned with what Seneca would have said versus a modern-day guru on Twitter/X.

2. The amount and quality of effort put into instructing the model - that is, old-fashioned continuous human-assisted feedback.

3. The ability to train a large enough model, appropriately matched (in terms of the number of parameters) to the size of the dataset.

The bottleneck is actually not (3), but (1) and (2). Training the model is mostly just money and fixed time (not to minimize the effort going into optimizing and managing training pipelines, but it is still reasonably straightforward), while (1) and (2) require a lot of custom infrastructure (both compute and human), sufficient user feedback (how many users are using the platform), a lot of (indeterminable) time and is quite error prone. The outcome is highly sensitive to quality data and feedback. Finally, it inevitably raises a number of legal and data ownership issues. Most importantly, these advantages (or lack thereof) will compound over time, making it largely a winner-take-all game.

So - how probable is it that open-source LLMs will catch up? Not very. That’s not to say that there’s no room for smaller task-oriented models (i.e., classification tasks) - but it is hard to see, short of a seismic shift in how data is shared and infrastructure is made available, how open-source/small players will be practically viable in a general-purpose sense.

I should also mention the dangers of overdoing the fine-tuning step. You can kind of see that with the constant flux of quality with well-known public models as they kept being fine-tuned for safety, etc. Fine-tune it long enough - and you will get mostly canned answers (an phenomenon known as catastrophic forgetting. Fine-tuning in general, without the access to the original data and training artifacts is tricky (for obvious basic reasons) - that’s why releasing “open-source” model weights without releasing the original dataset is hardly “open”.

Now - what about AGI that people are so concerned about? Here, you must agree with Jedi Master Yann LeCun that auto-regressive generation (LLMs) is “an exponentially-divergent diffusion process, hence not controllable”. Hence, ultimately, a new architecture, combined with a practical way to efficiently learn and optimize to a world model, capable of hierarchical planning, is needed. So far, this is nowhere in sight.

In the meantime, we have to do the latter part by hand, via software (even though written with assistance from LLMs), where LLMs become like building blocks in the operating system.

What does this mean then for the ecosystem and for us as humans? Here are some possible outcomes:

Jobs

While everyone is talking about many jobs that will become unnecessary for humans to perform, a more important question is: what kind of jobs will be created instead?

It is already clear that “clean high-quality” data is the new oil. Human expertise that can be put to use to improve these data (in a broad sense, including expert fine-tuning) is necessarily going to be valuable. Hence, it is not a stretch to imagine people will be paid to instruct the models.

For example, a legal brief can be presented to several top lawyers for a review, or a code PR can be presented to top coders for review and be incorporated into the model. Tools and services that enable that will therefore be new machine tools for humans. Of course - AI will determine how much those humans will be paid, possibly in AI usage credits 🙂

The inept regulation could become a monkey wrench for the ecosystem and the progress - yet, if done reasonably well, could take society to the next level.

Model Wars

It is hard to see open-source or second-tier LLMs becoming practical due to data and effort limitations, and it is not likely that hardware advancements will be overly impactful (considering the constant need to improve quality/performance/costs, and there’s still a long way to go there).

Furthermore - if, shall we say, a major player has a large, good-quality LLM with all the datasets and infrastructure - it is easy to downsize it and produce special-purpose small models almost at will.

The overlooked point here is that when one has the infrastructure to collect and manage data and feedback - that affords an interesting advantage at scale. Companies like ‘s Scale.ai could be extremely well-positioned here in the long run.

The Software

Until radical new architectures come into play, a combination of LLM pipelines will need to be used to construct applications. Dynamic performance will be increasingly important as LLMs continue to be exceedingly resource-hungry, and multiple interactions are required to produce a good-quality outcome. What are the components of such frameworks:

- Inference pipeline execution/orchestration - both in streaming and batch fashion, focused on controlling response times, failure management, costs, and routing between different task-specific models.

- The routing logic needs to be a lot more sophisticated, controllable, and self-programmable.

- The usual conveniences for prompt management, context, history, tools, and RAG.

- Multi-modal/image/video side of the world will more commonly need to be incorporated.

- User feedback response and dataset management for fine-tuning.

- System performance evaluation/testing in a continuous fashion, especially when more advanced fine-tuning tricks are used (such LwF and EWC).

The bigger elephant in the room is Python. While super easy to use and convenient, it is arguably a JavaScript/Ruby/Perl-class language in terms of its (non)-safety, extreme error-proneness (that exponentially compounds with larger teams), and (lack of)-performance. So - either a JIT-enabled and a syntactic layer (akin to TypeScript) is going to need to be invented, or we are going to need a lot more multi-language frameworks to go mainstream.

One interesting evolution to observe will be how much of self-writing code capability will be incorporated natively into the frameworks (and their evolution) themselves to produce a truly LLM-first system.

Let’s see how this ages.

Happy New Year,

Ruslan

“I don’t count my sit-ups; I only start counting when it starts hurting because they’re the only ones that count.” - Mike Tyson

In my earlier post, "My Personal Daily Routine," I described in detail the types of exercise routines I use and the rationale behind those choices. Here, I am going to outline precisely my current exercise regimen - with a disclaimer that I do change things up from time to time.

This regimen is based on a blend of several guided Beach Body workouts. The choice of Beach Body is purely historical as I am a long time user since P90X came out. There are many other excellent choices.

In "My Personal Daily Routine," I also go into detail as to why I prefer guided workouts - and yes, you can't listen to the All-In Pod while doing it, on purpose - unless you are doing Zone 2 training on an elliptical).

The overall length of the circuit is 10 weeks (6 weeks of it is based on 6 Weeks of the Work by Amoila Cesar and 4 weeks is based on Body Beast by Sagi Kalev with several routines from T-30 by Hunter McIntyre and other programs along with running / elliptical workouts).

I exercise every day and don't have a formal rest day. That said I will throttle the intensity, when I feel I am not fully recovered (based both on subjective and objective metrics), such as sleep quality, resting HR, HRV, respiratory rate etc.).

As you have noticed, the workouts are front-loaded in the morning and are of considerable intensity. This is a compromise within my schedule - as I am able to burn enough calories to not worry about the exercise and energy expenditure for the rest of the day.

A quote from Mike Tyson is important. In order to get an adaptation, we need to push it. So whatever recommended reps and loads are - those are just for reference. You need to continue to push it up (provided you are fully recovered and the form is not compromised). For example, if you did the last set of bicep curls with 30 pounds, go up to 35 next time (even reps go down) - and if you don’t have 35s and just did 8 reps with 30s and feel like you can do more with good form - well do 2-3 more.

Every workout starts with a 10-15mins foam rolling routine and I never skip it. Makes me feel like a teenager all day long.

The week for me starts on Sunday.

The first 6 weeks:

The 6-weeks of the work program consists of 3 blocks of 2 weeks each comprising of a mix of 5 different functional routines followed by a 20-25 mins recovery routine on the 6th day with 1 rest day in the middle. As I mentioned earlier - I don’t do rest days, therefor I use a modified schedule.

Sun, Mon, Tue, Wed, Thu is the appropriate sequential workout from 6-weeks of the work with a requisite recovery routine (called Range & Repair) followed right after the last weekly workout on Thu.

Fri - whatever I feel like a full body workout or an MMA-focused workout (could be as free form as practicing Krav Maga moves), optionally followed by a 30-mins Zone 2 on an elliptical (depending on how intense / long was the main workout).

Sat - 50m elliptical Zone 2 workout followed by a T-30 chin-up routine, followed by T-30 Sheriff Abs, and ending with a short stretch.

In addition (after the main workout):

On Sun - a short interval run (or a simulated run using an elliptical) consisting of 3m warm-up jog, 9 intervals of 1 min on / 1 min off followed by a cool down, followed by a 5-min stretch.

On Wed - a long intervals run (or a simulated run using an elliptical) consisting of a 3m warm-up jog, 3 intervals of 5 min on / 2 min off followed by a cooldown and a 5 min stretch.

On Mon for weeks 1, 3 and 5 (the 6-weeks of the work legs routine) - a T-30 pull-up routine, followed by a 10min Ab-routine from Insanity Max 30.

On Tue for weeks 2, 4 and 6 (6 weeks of the work Cardio & Core) followed by a 30min Zone 2 on an elliptical. Cardio & Core is the easiest workout in the series and the day overall feels like a rest day.

I am sharing the exact weight and rep ranges for me here. On T-30 pull / chin ups I normally go up to 12 reps on the ladder (unassisted). Of course this is with a maximally good form and with a minimum amount ego, making these weight / rep ranges quite challenging every time.

The last 4 weeks:

Sun: Beast-Up Chest/Shoulders/Triceps followed by T-30 short intervals.

Mon: Beast up Legs, followed by a T-30 pull-up routine.

Tue: Beast Cardio followed by Beast Abs optionally followed by a 30min Zone 2 on an elliptical.

Wed: Build Back/Biceps optionally followed by a 30min Zone 2 on an elliptical. This is one of the toughest workouts in the series and Zone 2 here is truly optional.

Thu: Bulk Shoulders (Thursday #1), Bulk Chest (Thursday #2), Bulk Arms (Thursday #2), Build Chest / Triceps (Thursday #4) or a similar auxiliary lift followed by T-30 long intervals.

Fri: Beast Total Body or if feeling really good, Week of Hard Labour: Total Body (another program by Sagi Kalev) followed by a recovery routine.

Sat - 50m elliptical Zone 2 followed by a T-30 chin-up routine, followed by a T-30 Sheriff Abs routine, and ending with a short stretch.

Unlike 6-weeks of the Work routines - these are done with heavy weights - and I mean heavy.

Why it may look like the last 4 weeks are more demanding - they are not. 6-weeks of the work type workouts focus on compound and power movements putting a lot of stress on a neuromuscular system, so these 4 weeks feel like a break.

All of this is not set in stone, and I do vary and experiment with things from time to time. When I have to shorten the workout, the ab routines get skipped as they are the least essential.

Enjoy!

DISCLAIMER

This content focuses on the subject of mental fitness and its impact on performance, reflecting solely my personal experiences. Please understand that the tools and methods mentioned are not intended as medical or any other kind of professional advice.

Everyone faces challenges in maintaining emotional balance under life's stresses, whether they're outwardly visible or not, and this invariably affects our performance in various professional and life situations. Looking back with hindsight, I can attribute most of my past mishaps to my failure in maintaining emotional balance, which led to less than optimal judgment, poor timing of actions, or ineffective communication with others.

It took me many years and several attempts to unlock some of these doors, and I've reached a point where I feel it might be useful to share my insights. I'm sharing these thoughts reluctantly, fully aware of our individual differences and the complexity and subjectivity of this topic.

The basics

“If you can’t tell what you desperately need, it’s probably sleep.” 

— Kevin Kelly 

Before trying to fine-tune our brain's software, it's crucial to ensure that our hardware is in the best possible shape. This involves optimizing our sleep, exercise, and nutrition. I have always tried to take care of these fundamentals, and while they aren't sufficient on their own, they certainly make the rest of the process much easier.

My personal daily routine, which mainly focuses on sleep optimization, exercise, and nutrition, is documented here for reference. I recently made several updates there, so take a look.

Physiological Stress management

Obviously operation or programming of the brain doesn’t work well under stress. However, there are several well-supported strategies to mitigate this, some of which are deceptively simple yet effective:

1. Being in nature

2. Breathing (there’re many methods), the main two I use:

   1. Box / Tactical breathing (called tactical because it is used in combat situations to calm the mind). I use a very simple iOS app called Breethe+ where you can set your own intervals. The classic box breathing would be 4s in 4s hold 4s out 4s hold (4-4-4-4 - the box). The exact inhale/exhale/hold intervals are actually empirically discoverable for each individual. Search for CO2 tolerance test.

   2. Physiological sigh: double inhale - long exhale (audibly of possible, almost like going down the slide). The basic idea here is that when exhale is longer then inhale - it lowers adrenaline, the reverse raises it. This technique been used in martial arts since the beginning of time.

3. Combining breathing with specific gaze patterns or tactile engagement with objects around you (such as toying with items on a desk during a meeting) can also be helpful.

4. A cold shower or plunge can temporarily increase dopamine levels. While I can confirm its benefits, I don’t particularly enjoy it. Nonetheless, some people swear by it.

5. Completing an unrelated (but necessary) small task, even if a distraction).

These methods not only influence neurotransmitter activity and heart rate but also allow you to subtly co-opt your autonomic nervous system for better equilibrium.

Finally, it's worth mentioning the "letting go" technique from David Hawkins's book, which provides another approach to managing stress.

Stress conditioning

Martial arts training has the unique advantage of preparing you to perform under stress. One of the initial drills I recall vividly involved standing with closed eyes while teammates would strike from various directions. The hits weren't overly painful, but they were certainly noticeable, and the task was to just stand there and take it. It was quite an unsettling experience at first.

In a similar vein, both the Stoic practice of visualizing negative outcomes—referred to as "Premeditatio Malorum" (contemplation of future adversities)—and deliberately setting up challenging situations (fasting, cold showers again, United Economy, long useless meetings - well may be not those ones) are all good methods depending on what it is for you.

Mental energy management

I would also emphasize (from experience) that mental performance is closely tied to effective energy management. Possibly this is one of the most important aspects to pay attention to.

When your nervous system is drained—whether from excessive work-related stress, a series of unfortunate events, or intense physical exertion, especially from demanding full-body functional exercises—taking a break is often the best course of action. This could mean a change of pace, total disconnection, or simply some time to relax. Those of us with type-A tendencies often overlook the need for rest, but it's crucial to acknowledge that sometimes, the best thing to work on is allowing ourselves to recover.

Having a stress score from a wearable, such as an Oura ring, can be a good prompt. Not that you don't already know it, but empirical confirmation can serve as a useful behavioral tool to prompt action.

Managing thoughts

“If You Think You're Enlightened, Go Spend a Week with Your Family”

- Ram Dass

It would be more accurate to call this section 'Managing Thoughts and Behaviors.' The basic idea is that by consciously replacing undesirable thought patterns and behaviors with desirable ones, we can reprogram our thoughts and eventually our subconscious to be more effective. Cognitive Behavior Therapy (CBT) has been around for a while and exemplifies this concept.

Of course, it's easier said than done.

There are clear parallels with sports, particularly martial arts. It might take 30-40 repetitions to learn a new movement, but unlearning a faulty one can require up to ten times more. We can control physical movements relatively easily, practicing slowly, using a mirror, or working with a partner, and these movements aren't overly complex.

Now, apply this concept to the mind? That requires a lot of training iterations. This is why therapy can take years and yet yield only marginal results. The sheer number of repetitions and variations is overwhelming.

However, that doesn't mean we shouldn't try.

I've become a big fan of the Stoic toolkit. After several years of practice, I've found it easy to learn, apply, and quite effective. I like simple things.

This isn't to undermine CBT or its more advanced forms like DBT, which have their useful tools. Albert Ellis, who developed REBT (a precursor to CBT), was significantly influenced by Stoic philosophy.

I prefer going to the source. The Romans excelled in combat, enjoyment, and wealth creation. It's a simple, time-efficient framework that's easy to apply.

The first real book I read on stoicism (outside of school) and apart from occasional skimming through Meditations was The Practicing Stoic by Ward Fransworth and I can’t recommend it highly enough.

I quickly realized that you do have to actually practice it and then stumbled on another resource that I think is absolutely awesome: A handbook for New Stoics by Massimo Pigliucci that is structured as 52-week long lesson journal for each week.

Finally, I read a page every morning from an excellent book The Daily Stoic by Ryan Holiday.

I most certainly don’t feel qualified to explain stoicism, yet I feel I must offer a condensed (while incomplete) list of key concepts and practices to give you a sense on how I apply it:

To succinctly capture the essence of Stoic philosophy, it is perhaps best expressed in the words of Epictetus himself:

“There are three things in which a man ought to exercise himself who would be wise and good. The first concerns desires and aversions, that a man may not fail to get what he desires, and that he may not fall into what he does not desire.

The second concerns the movements (toward an object) and a movement from an object, and generally in doing what a man ought to do, that he may act according to order, to reason, and not carelessly.

The third thing concerns freedom from deception and rashness in judgement, and generally in concerns ascents.

Of these topics the chief and the most urgent of which relates to the effects; for an effect is produced in no other way than by a failing to obtain that which a man desires or falling into that which a man would wish to avoid. This is that which bring in perturbations, disorders, bad fortune, misfortunes, sorrows, lamentations, and envy; that which makes men envious and jealous; and by these causes we are unable to even listen to the percepts of reason.”

- Epictetus. Discourses 3, 21-3

In plain terms - Stoicism can be divided into 3 disciplines: The discipline of Desire (or wish), the discipline of Action (or impulse to act) and the disciplines of Accent (or judgements).

Key practices:

1. Dichotomy of Control: Recognizing the difference between what is in our control (our own thoughts and actions) and what is not (external events and others' actions), and focusing our energy only on the former. Once you think about it - you realize how little is truly in your control.

2. Mindfulness (Prosoche): Maintaining a constant awareness of our thoughts, actions, and feelings in the present moment to live intentionally and virtuously. Training in mindfulness mediation is extremely helpful as it allows to bring up some of the awareness you achieve while quite into a busy life. I actually doubt it’s otherwise possible purely on the intellectual level, without a formal meditation training. Almost like you can intellectually think how to punch correctly, but unless you practiced under stress - good luck.

3. Journaling (Meditation in Stoicism): Reflecting on one's thoughts and actions through daily journaling, which serves as a tool for self-improvement and self-reflection. My sense is - everyone has to find his or her own path here. I cycled through many formats until I arrived at my own and I am still constantly tinkering with it from time to time depending on circumstances. The point is to just do it.

   Here’s my current format in Apple notes:

   

4. Premeditation of Adversity (Premeditatio Malorum): Visualizing potential challenges and setbacks to prepare oneself emotionally and mentally for adversity and to diminish fear of the future. You can visualize both negative and positive outcomes (the latter is not technically Stoic - but could be useful for other purposes). Again - something you do in martial arts (i.e. visualizing an adverse scenario and the execution of various techniques in response). The important part here is not just to think about it - but try to engage all senses (smell, touch, taste) and feelings if possible.

   A word of caution (speaking from experience): negative visualization is a double-edged sword, because we really don’t want to manifest bad things, just prepare for if/when they come. Especially when all senses are engaged it influences “reticular activating system" (RAS) - a network of neurons that is involved in discriminating incoming information into important versus background noise. I suspect this is where “make believe” problems tend to come from.

5. The View from Above: Practicing a mental shift of perspective, imagining looking at one’s life from a cosmic perspective to gain a more objective and less egocentric view of events.

6. Negative Visualization (Memento Mori): Contemplating the impermanence of life (or just about everything else for that matter, possessions, relationships, money, etc) and the inevitability of death to value the present and live life more fully.

7. Amor Fati: Embracing and loving fate, which involves accepting and even welcoming the events that occur, as part of the natural order of the universe.

8. Virtue Ethics: Striving to cultivate personal virtues such as wisdom, courage, justice, and moderation in all aspects of life.

9. Sympatheia: Acknowledging the interconnectedness of the universe and the kinship of all beings as part of a larger human community. This one has actually been genuinely hard for me.

10. Voluntary Discomfort: Occasionally practicing self-denial or undergoing hardships to increase one's gratitude for what one has and to build resilience against future discomforts.

Some of these practices may be easier or harder for you. But like Arnold would say - “you have to work on it”.

Trust this is enough of my pontifications on this subject. I would encourage you, if you find this helpful, to go to the original sources. Epictetus and Seneca's letters are great resources.

There is one more helpful tool in the toolbox I use - and this is from the book Loving what is by Byron Katie. The 4 questions are:

1. Is it true?"

2. "Can you absolutely know that it's true?": a bit of reductio ad absurdum, but it works …

3. "How do you react, what happens, when you believe that thought?".

4. "Who would you be without the thought?"

The process also includes a "turnaround," which involves considering the opposite of the original belief.

While the framework is super simple, I’d recommend listening to the entire book on audio specifically for situational examples.

Hope this helps! Remember, these tools are for programming your neural nets and aren't very efficient because we're attempting to reprogram our behaviors using the conscious mind. Choose methods that feel natural for you, and avoid getting overly wrapped up – these are just tools in the tool box.

Managing emotions

"No amount of anxiety makes any difference to anything that is going to happen.”

- Alan Watts

There's a long-running debate about what comes first—thoughts or emotions. They are likely interdependent, something we have all experienced. You feel something in your gut, you start thinking about it, and one thing feeds the other. This is the interplay between the conscious and subconscious. It highlights how incredibly difficult it is to control the subconscious with a conscious mind and who is really in charge most of the time.

There’s a school of thought (and quite persuasive at that) which argues that we have no free will. Either way, we're interested in affecting the programming, which is also ironic—because it, of course, implies that there's a programmer, which would not be consistent with a non-dualistic worldview. So here you have it—several cans of worms at once.

Back to the task at hand. The goal here is to bridge the gap between the emotions (the unconscious) and the thinking mind so that both can be complementary and in coherence as much as possible. After all, we do want to have access to the lower (at least our executive mind thinks they are lower) layers of the stack. You see the analogies in the corporate world, no doubt 🙂

The first thing to understand is that we do need to go down the elevator—that means we have to get out of the Beta brainwave state and drop at least into Alpha, and ideally Theta. That's why I meditate in the morning, just right after waking up (as the brain is still transitioning out of Theta).

So, meditate first thing in the morning if at all possible, in a quiet place that allows you to settle and relax. That's what I do. Yes, that means absolutely no checking of email, Slack, or Teams (if that's your world). Twitter/X is Ok - just kidding, absolutely not.

There are methods, of course (such as the countdown technique), to settle the mind, but these can take considerably longer in the middle of a busy day. We are still all about efficiency here.

As I've mentioned before, I use the excellent Waking Up app by Sam Harris. There are other options as well, and I’d say experiment to find what works for you. That said, in my personal opinion (having tried most of them), Waking Up is hands down the superior choice by a mile and is completely free of fluff. At some point, the app also becomes optional.

It took me years to start noticing the effects (probably at least 1.5 years). I am a slow learner. In fact, for the first six months, I constantly questioned myself—why am I doing this? It’s not working. Then, progressively, it clicked into place.

By far the first benefit is that you start noticing your thoughts and emotions, and that ability to observe becomes stronger and stronger and progressively transfers into daily life as well.

That noticing opens up additional contemplative opportunities:

1. Simply an ability to examine thoughts and ideas without overwhelming ego interference

2. Use the power of visualization to set intentions

3. Start appreciating the present moment, improve attention and enhance gratitude, that I think does lead to a greater happiness (or lesser unhappiness)

Try it.

What about neurofeedback wearables? I've tried several, and none worked for me. Perhaps individual brain circuitry varies, and for some people, external feedback is useful. For others, especially those with meditation training, it just adds an extra layer of delay and thus becomes counterproductive. Who knows?

The Universe, Intuition and Intention

"You are not a drop in the ocean. You are the entire ocean, in a drop."
– Rumi

The nature of the universe and our relationship to it has been a subject of contemplation by many brilliant philosophers and physicists since the dawn of time. Obviously, we cannot claim to know substantive answers—just as an ant cannot comprehend the life happening above it. Nonetheless, grounding ourselves in a model of understanding, however tenuous or circular it may be, can still be helpful as we navigate, act in, and act upon this world.

While there are countless books and writings on the subject, they remain largely theories or, more often than not, conjectures—most of which are inherently non-falsifiable. This means they cannot be definitively proven or disproven, placing them in the realm of philosophical exploration rather than empirical science. As such, they must be approached with a healthy dose of skepticism and an understanding of their speculative nature.

That said, when we look across the breadth of world philosophies and spiritual traditions, unmistakable patterns emerge—seemingly independently—and some of these recurring ideas become difficult to dismiss outright. While they may not meet the rigor of falsifiability, their persistence across time and cultures suggests they offer valuable lenses through which to view our experience of reality.

I’ll recommend a few resources that I find practical and thought-provoking:

• Two books by Rizwan Virk:
  Simulation Hypothesis and The Simulated Multiverse. The central question is: Are we Player Characters (PCs) or Non-Player Characters (NPCs)?

• A Brief History of Intelligence: Evolution, AI, and the Five Breakthroughs That Made Our Brains by Max Bennet offering a non-metaphysical view on development of human mind

• Vadim Zeland's Reality transurfing series:
  In particular, Transurfing in 78 Days — A Practical Course in Creating Your Own Reality. This book is similar in format to The Daily Stoic, offering structured daily reflections. At its central is the idea of viewing the world as a mirror—a concept drawn from many traditions but most closely aligned with Dao Qing, emphasizing harmony and the dynamic interplay between inner intentions and outer reality, a perspective that Zeland’s work echoes.

Intuition

We all know what intuition is—the simplest example being a “gut feeling.” You can debate whether it comes from within (as some sort of autonomic AI within us) or from external influences—or perhaps a combination of both. What’s undeniable is that intuition can be profoundly helpful. There are many who hone this skill, learning to quiet the noise in their minds to reliably tap into their intuitive sense.

The good news is that there are techniques, many of them rooted in spiritual traditions, that can sharpen your ability to listen to your internal voice. A resource I particularly like is The Intuition Bible: How and Why to Tap Into Your Inner Wisdom by Happy Ali. It offers a solid list of techniques you can experiment with yourself.

Intention

Our intentions are the engines that drive us to act. However, the real challenge lies in maintaining sharp focus on our goals, especially in the face of distractions, a racing mind, or low energy. Frederick Dodson’s Reality Creation and Manifestation outlines a number of focusing exercises that I’ve found practical. These are well-known techniques that can likely be found elsewhere, but Dodson presents them in a clear, actionable format.

Final Thoughts

Some of the books I’ve referenced are less than scientific, and they contain ideas and assertions you may not agree with—or even find contradictory. That’s okay. You don’t have to fully align with an author’s worldview to benefit from their ideas or techniques. Take what resonates, apply it where it’s useful, and leave the rest.

Navigating the path

"It is not your responsibility to finish the work [of perfecting the world], but you are not free to desist from it either."

-l Rabbi Tarfon, Pirkei Avot 2:21

It is self-evident that we, as humans, have an inherent motivation to create, contribute to, and improve the world around us. We know when we are succeeding on that path, and we equally recognize when we are not.

So, how do we figure it out? The first sign is usually a feeling of being off course, which we recognize after some time. The natural—and correct—evolutionary inclination is to change course. But how do we optimize this search and minimize the chances of being misled by the impulses of the ego?

3MQ method

It represents the three most important questions I learned from Vishen Lakhiani’s work. The questions are:

1. What do I want to experience?

2. How do I want to grow?

3. What do I want to contribute?

The format is a one-pager, like this (a Google doc is fine). The answers are, of course, something to be contemplated, ideally several times over a period.

In all these kinds of contemplations (just like with visualizations), it's important to engage all senses when describing experiences. Literally feel yourself speaking on that stage, hear the audience, describe the shapes of the lights, the temperature in the room, etc.

The life timeline method

The second method I've found useful is to map out my life's timeline in manageable increments (like 1-2 years), akin to an OPS post-mortem. I jot down important points about these periods and try to identify Kensho and Satori moments.

In Zen Buddhism, "Kensho" means "seeing one's true nature" and refers to a sudden insight or awakening. "Satori" is similar but considered more profound and enduring. Kensho is often characterized as enlightenment gained through adversity or suffering, whereas Satori is seen as a deeper, more comprehensive awakening or enlightenment. (this is a very non-nuanced explanation—my apologies). As we examine the timeline, these moments and experiences should become self-evident.

Finally, an excellent book, "The Second Mountain" by David Brooks, which was recommended to me, was also quite helpful.

This discussion would not be complete without talking about what everyone is talking about these days - and that is what’s the place in this exploration for the use of entheogenic aids.

Obviously the promise here is bypassing the conscious mind and - back to the AI analogies instead of prompt engineering do the full fine-tuning of the model, with all the requisite risks of course.

This is not something one should attempt casually and only do it a jurisdiction and within the framework where it is legal and in a safe set and setting, with the appropriate medical evaluation (there’re several serious counter-indications), supervision and pre/post integration. This type of exploration should be taken very seriously, otherwise it will not only not work, but can cause serious harm.

Below is a compilation of resources that might be helpful:

1. The first book everyone reads is How to Change your mind by Michael Pollan

2. Then of course there’s Food of the Gods by Terence McKenna

3. A more practical collection of research and clinical experiences mostly from the before the ban era by James Fadiman

4. There’s a lot of emergent research that may be worth paying attention to, a good destination for that is MAPS

5. Should you want to see what pushing the envelope looks like: LSD and the Mind of the Universe: Diamonds from Heaven by Christopher M, Bache.

In the vein of ancient Greek philosophers, the specifics of such journeys tend to remain unspoken, varying widely from individual to individual. Nevertheless, here's what one might generally expect:

1. Allocating around 5 weeks for a well-structured process seems to be a common practice:

   1. The first two weeks are for preparation. It's usually recommended to continue with regular work but to avoid unusually stressful situations. Abstaining from alcohol is required, along with maintaining a healthy diet (which one should do anyway). The real challenge is the need to forego coffee.

   2. A week of actual retreat.

   3. Following this, two weeks of post-integration are necessary. With increased brain neuroplasticity during this time, minimizing stress and focusing on contemplation is more crucial.

2. Approaching this experience with intention, yet being open to new insights, is often advised. A three-session protocol within a week has been known to be effective for allowing these realizations to emerge and facilitating thorough exploration.

3. It is often noted that the future remains a mystery, filled with myriad possibilities. This resonates with the belief that the Universe—or any higher power one subscribes to—is in a perpetual state of exploration, with each person acting as an explorer.

4. The dissolution of ego, acute focus, and a clear view of one’s life history enable an unfiltered perception of reality, often described as liberating from the usual mental noise. This can be challenging at times, but many report a clarity where excuses and justifications simply vanish, leading to an acceptance of reality as it is. In such moments, the relevance of preparation is frequently recognized in hindsight.

5. The path often becomes clearer during this journey—gaining an understanding of one's purpose, the reasons behind certain life events (not in a deterministic sense, but in a way that renders the unfolding of events logical, given the inputs and circumstances), and the potential paths ahead.

6. The high degree of focus may persist for several weeks.

7. Regular meditation practices tend to improve significantly, sometimes enabling brief re-experiences of the journey’s state.

8. A noticeable increase in kindness towards others, compared to one's usual behavior, is often observed.

9. It is suggested to keep a notebook close for reflections during and immediately after the experience. While the memories may remain intact, capturing the clarity of specific insights could be valuable.

The final question here is—can this be achieved without pharmacology? While the answer is obviously yes, as centuries of spiritual traditions confirm it, the practicality can be a challenge.

Some options include long meditation retreats, holotropic breathing sessions, and insights could also result from Kensho-type moments. However, none of these are reliable, time-efficient, or (in the case of Kensho moments) necessarily desirable (or predictable).

Hope this helps.

I'd certainly heard about coffee withdrawal syndrome from others, and that it's not pleasant. Given this, I wasn’t eager to experience it. However, being the biohacker that I am, I viewed this as an opportunity for a self-study.

My Normal Coffee Routine

As I've mentioned, I love coffee. I drink it black, no sugar, often a robust Americano made from 2 double espresso shots. I savor its taste, akin to the way a wine connoisseur would. My go-to is Black Cat Espresso, but I do enjoy Taiwanese coffee when I can find it.

Here's a breakdown:

• Legion Pre-Workout drink (1/2 serving): 175 mg (early AM)

• Americano (2x double espresso): 280mg (for breakfast, using an average double espresso estimate of 120-160 mg)

On occasion, I might have another coffee after lunch. But these instances are rarer these days due to its impact on my sleep quality, not in terms of how long or how quickly I sleep, but the depth and quality of it, as shown by my Oura ring data.

The Ramp-Down Protocol

To cut back on caffeine, I followed these steps:

• 4 weeks: No second coffee during the day.

• 3 weeks: Substituted my Americano with a decaf version (still Black Cat Espresso) and no coffee after lunch.

• 2 weeks: Shifted to a non-caffeinated version of the Legion drink.

The first and second steps, particularly the switch from caffeinated to decaf Americano, were smooth. Completely cutting off caffeine led to a mild discomfort around day two, but it wasn’t as dreadful as I'd anticipated.

Subjective Experience

The absence of coffee brought noticeable changes. My workouts, especially in power lifting moves, weren’t as good (quite lousy actually to be frank). My thinking felt slightly slower.

However, the days did have a notable calming effect. My focus sharpened and my ability to get into the flow of tasks improved.

But, even when using the same brand, decaf didn't quite hit the mark in taste compared to its caffeinated counterpart.

Objective Data

The data is somewhat hard to interpret and comes off as noisy; the experiment likely needed more time for clearer results. The Oura ring, though good in comparison to other devices, isn't entirely accurate, particularly regarding sleep stages. Their recent statistics indicate a 79% agreement with polysomnography, which isn't as impressive as one might hope.

With those disclaimers in mind, you can see a discernable improvement in sleep quality and especially deep sleep. Interestingly, sleep latency didn't seem to be affected, suggesting that mechanisms beyond just the blockage of adenosine receptors, like hormonal regulation, might be at play.

My blood pressure exhibited a significant drop, which could be a potential reason for the decrease in workout performance. It's worth noting that I measure my blood pressure using the Omron 10 Series monitor, in the mornings. Since I don't strictly adhere to guidelines like remaining still for a while before taking measurements (in the interest of time), the absolute readings are somewhat higher (by 5-8 points) than a precise clinical measurement.

Ramp Back Up Protocol

Getting back on caffeine mirrored the wind-down:

• First up was the caffeinated Legion pre-workout.

• A week later, my regular Americano returned.

With the reintroduction, I observed:

• A bounce-back in workout quality.

• Faster thinking.

• A delightful Americano experience once again.

My blood pressure saw a slight uptick but remained below my initial readings. The sense of calm I experienced earlier started to diminish, as did some of the increased focus. While sleep quality did decline a bit, it was surprisingly still better overall.

And all this was after the retreat, which could have influenced some of these observations.

Parting Thoughts

The big takeaway? Living without coffee is feasible. The effects of withdrawal are manageable. Yet, there are trade-offs:

• Sleep: Coffee, even just in the morning, does affect it.

• Focus: There's a definite improvement without caffeine.

• Mental Speed & Workouts: They thrive with caffeine.

• Decaf: Doesn’t taste quite the same.

To wrap up: Would I quit coffee entirely? Hell no. But considering breaks based on my observations? It's a possibility.

Until that time, as an individual contributor in previous companies, I had experienced the performance review process, but it never registered. Like most people, I would look at the compensation adjustment line and the rating, ignore all else, and move on.

This time, as an engineering leader, the full rollout of the performance review process, complete with 360s, ratings, ratios, calibration sessions, and the SuccessFactors software, caused some visceral feelings. Here are some things that went through my mind in that meeting:

1. Time commitment - while it was being sold (as all new processes are sold that way) as “lightweight,” even then, it was clear to everyone that it wasn’t going to be. Mind you, being understaffed and overworked wasn't even beginning to describe the degree of burnout we then experienced. After all, the 9/9/6 schedule is a Silicon Valley invention, and we had a 9/9/6 Plus (we loved it though in all fairness).

2. We had great and highly complementary teams in terms of skills - it was a head-scratcher for me how I would rate people in that situation where there were no obvious underperformers, and everyone was giving it their all.

3. I was most worried about the downsides of the process. Hiring was extremely difficult in those days, and losing a key engineer or two because of an artificial rating almost guaranteed a major adverse impact since we had single points of failure just about everywhere.

Being rather naive at the time, I shared my reservations in that meeting and asked why we needed to focus on performance reviews. I still remember the answer that is worth pondering on: “Because it is Best Practice.”

Let this sink in - "We are going to be implementing X because it is a Best Practice.” Take your favorite pick where we heard a similar explanation or a variant of it. To this day, I keep failing to find any evidence of this practice being positive at all, let alone “best,” from whatever scant research there has been.

Perhaps someone has done or is going to do a well-designed study (even a retrospective one) on the topic - if you know of one, please point me to it. Here's what I have observed in my experience across several companies (as well as heard from other managers and executives):

1. There seems to be an uptick of regrettable departures (people we don’t want to quit) right after a performance review cycle.

2. Performance calibration meetings are one of the more toxic events in the company, often preceded by a massive amount of horse-trading among managers and executives and a lasting ill will afterward.

3. Compensation adjustments following the reviews are always below what people expect and are (on average) a negative retention driver (if you want to retain someone for comp reasons, you better adjust the comp out of cycle).

4. The amount of time spent on the process is material in terms of delivery and focus, and of course, those magically fall into the end of the quarter. I would estimate at least 1 full month of productivity lost.

5. No one likes the performance review process (not to be confused with what you hear from HR surveys - when people say they want feedback through the review process - they want a raise or a promotion).

Now, to be dialectical about this problem, let's look at it from the point of view of a CEO. Why would a CEO need to have a performance review process within the company? There are several good reasons:

1. We need to understand how to manage compensation adjustments within the company, hence we need to understand the performance rankings.

2. Similarly, we need to make sure we manage out underperformers on a regular cadence.

3. We may have managers within the company who are new or inexperienced and not doing performance management.

4. We want to put some objectivity into the data - and not rely on managers only, hence the 360 feedback.

5. We want to have a process/documentation to manage performance for compliance reasons.

6. As the company grows, the individual performance matters less than elevating an average, hence we’re less concerned with the impact of regrettable attrition - but rather with managing the average performance of the organization (the usual curse of a big corporation).

7. We just hired a new Chief People Officer 🙂

Any process that involves people is an attempt to program people's behavior towards specific goals. It works best when groups are small and goals are clear. When groups are small, you don't need performance reviews. In a bigger company, I would argue that neither is true, nor are objectives clear (a fair distribution of a token comp adjustment, an overdue promotion, or identification of already obvious bottom performers are hardly that).

So, if it is about programming organizational (and individual) behavior, we are going to need to approach it from first principles and in more subtle ways.

To be continued.