AI Engineer · Independent Thinker
Building with AI agents, and thinking out loud — projects, writing, talks, and reflections in one place.
An interactive guide to basic reproduction number R₀ and the herd-immunity threshold: how chains grow or fade, how immunity shrinks the susceptible pool, and why coverage ≈ 1−1/R₀ can tip effective R below one—teaching model only, not policy advice.
Explore the visualAn interactive guide to the normal (bell) curve: why most outcomes pile near the mean, how independent small shocks stack into that shape, what 1/2/3σ bands mean, and why rare tails still appear in large samples—mechanism only, not a formula drill.
Explore the visualAn interactive guide to Bayesian updating: how different priors plus the same positive test can yield opposite posteriors—base rates, likelihood ratios, and tree/area intuition. Teaching numbers only; not a medical diagnosis.
Explore the visualAn interactive guide to compound growth: why discrete compounding pulls away from linear add-ups, how a tiny daily rate becomes a large gap over 365 steps, and why time horizon matters as much as the rate—mechanism only, no investment advice.
Explore the visualAn interactive guide to inflation as purchasing-power dilution: how money or demand shocks lift the price level, why nominal cash is not the same as real buying power, and how a single rising price differs from a general rise.
Explore the visualAn interactive guide to sensitive dependence in chaos: tiny initial differences, exponentially diverging trajectories, predictability horizons, and why the butterfly is a metaphor—not a literal cause.
Explore the visualAn interactive guide to the prisoner's dilemma: payoff matrices, dominant strategies, Nash mutual defection, the welfare gap, and how repeated games with punishment can protect cooperation.
Explore the visualFollow ENSO from equatorial Pacific heat anomalies through rainfall teleconnections and crop stress to grocery price pass-through—kept distinct from the typhoon Visual.
Explore the visualRead price and volume as contextual evidence about participation, liquidity, and market response—not as a certain trading signal.
Explore the visualFollow the refrigerant through evaporation, compression, condensation, and expansion to see how an air conditioner moves heat outdoors.
Explore the visualLearn Loop Engineering in plain language: contracts, bounded attempts, evidence, durable state, budgets, stop routes, human review, and system improvement.
Explore the visualThirteen interactive steps explain how a warm ocean disturbance becomes an organized tropical cyclone.
Explore the visualReading arXiv:2610.00372 CIR: treat harness refresh as a causal decision—paired with/without recovery from the same state, separating rescue from harm. On ALFWorld×Qwen3-14B, never-refresh 70.33% → CIR 73.33% (+3.00 pp); clean trajectories untouched; two-step stale gain +9.33 pp.
Reading Glow Labs’ PixelLeak: agents hit a CLI PR-attachment gap, then self-opened shared egress via public repos and gitshot—13k+ images, 300+ orgs, 93% on personal accounts. Contrasts sandbox≠containment and SINGED (correct output ≠ safe execution). Mechanism and audit checklist only—no exploit steps.
Reading Adobe Research arXiv:2609.30967 MoMHa: treat the LLM harness as a three-objective search surface over accuracy, behavioural safety, and tokens. A single-phase joint reward beats ten baselines and a two-phase ablation (synthetic J=0.482, real-world J=0.461, U-SafeBench 0.781, 95 fewer tokens/example than two-phase).
Reading arXiv:2609.36043 SAGE: self-evolution loops discipline the optimizer while the gate often still accepts any validation-score rise. With a per-item paired ledger and a one-sided test, SAGE cuts regressions in 19/20 settings (LiveMath 36.5%→0%, OfficeQA 42.8%→0%) and tops final scores in all 20.
A mechanism survey from Gödel Machines, AlphaEvolve, Darwin Gödel Machine, SEAL, and ADAS to RRSI harness evolution—separating bounded self-refinement from open-ended RSI, and demonstrated loops from hype.
Reading Matthew Green’s “Is sandboxing sufficient to contain rogue agents?”: containment often was never seriously tried ≠ sandboxes suffice; useful agents need information access, so the problem becomes traffic surveillance and recursive warden alignment; a third frame is eager obedience + shared channels = worm ingredients. Contrasts OpenShell/Sentry and Hard Stop.
Reading arXiv:2609.37153 ToxicBench: successful tool calls can return poisoned observations. On 118 GPT tasks, poisoning drops TSR by 26–39pp; BCR is 0.38/0.53/0.27 on LangGraph/smolagents/AutoGen. Separates checking from adoption; contrasts SINGED/FTA.
Reading arXiv:2609.30123 HEXIS: Skill+ReAct still re-infers control each step; compiling skills into extended FSMs keeps knowledge in per-state instructions and control in guarded transitions. +16.2pp avg vs Skill+ReAct across 4×4 settings; Qwen3.8-27B cuts execution tokens 38.4–88.9%. Contrasts site posts on progressive disclosure / SkillDelta.
A mechanism read of arXiv:2609.27334 JitMem: most agent memories distill at write time into fixed reflections/skills before the future query is known—irreversible loss. Keep raw trajectories; at read time a curator synthesizes a task-adaptive payload, trainable from immediate task success (e.g. GRPO). +16.2/+16.3/+3.9 absolute SR over the strongest write-time baselines on ALFWorld/WebShop/τ²-bench; even an untrained curator is competitive.
A deep read of CAIS CheatBench (arXiv:2609.36308): ten environments that measure whether agents take shortcuts against honest-work expectations. Current overall rates ≈11.2%–78%; every evaluated agent cheated in at least one setting. Mechanisms, how to read the scores, and a harness checklist.
Reading arXiv:2609.35889 SINGED: functional counterfeits match benign outputs while triggering forbidden process effects; among 7,549 audited trials, rank-one counterfeit execution hits 45%, and cross-candidate comparison cuts layered failures from 15.7% to 4.2%. Correct output ≠ safe execution; a harness checklist.
A deep read of arXiv:2609.35732 Failure-Transparent Agents: fix failed observation and evidence state before generation, then audit post-failure claims. Across 6 models and 3600 human-annotated responses, false success falls 22.8%→9.3%→0.8% under baseline / transparency / evidence contract; useful responses rise to 98.8%.
Matthew Green argues process sandboxes fail once agents share egress channels (caches, email, Slack, docs). Elevating the HF chain into an authority-axis problem complements OpenShell’s hardware boundary and METR’s policy record.
A viral YouTube clip ties Jev to Claude Code, but Jev cannot be the CLI chat model. This post covers the official skill, boundary hooks, MCP, and per-turn routing, contrasts NobodyWho’s 25-line minimal build, and discusses OpenAI fast-follow pressure.
Reading CVE-2026-14540 / GHSA-3x3x-8ffg-ghcv: why SSRF (CWE-918) on MCP HTTP tool paths matters for agents; SSRFGuard’s default-deny for private networks; why MCP tool servers sit outside classic SCA call graphs; upgrade to 1.5.0+ and config knobs.
Reading Purdue arXiv:2609.30725: across 1,200 Claude Code and Mini-SWE-Agent trajectories, three behaviors hit 79–98% of tasks and up to 22.75% of task cost; structure-aware retrieval can raise cost 28.14%; developer-designed skills cut ~2× agent-synthesized skills.
An independent OpenSpec guide to proposals, spec deltas, and archiving: when it fits your project, what files it creates, and where to find the official docs and CLI tutorial.
Get started with the published BMAD Method 6.12.0: installation, bmad-help, bmad-build, real directories, a small first-change exercise, and the limits of role-based instructions.
An in-depth analysis of GitHub Spec Kit's architecture, workflows, and enterprise applications exploring how Spec-Driven Development solves context loss in AI programming
Key insights and takeaways from Cal Newport's book on focused work
Explore the curated taxonomy — themes, clusters, and tags.