Trust First, Then Parallel: What Lauren Tan's Talk Actually Argues
Lauren Tan: throughput comes from trust, not more agents. Five correction layers, verification skills, locked-down repos, and which numbers are self-reported.
Remy (Redreamality)
AI Engineer · Independent Thinker
Building with AI agents, and thinking out loud — projects, writing, talks, and reflections in one place.
Visuals
View all visuals Interactive explainer
Even a Fierce Virus: Why Does Spread Self-Extinguish Past a Coverage Threshold?
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 visual Interactive explainer
In a World of "About Average," Why Do Extremes Keep Showing Up?
An 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 visual Interactive explainer
Same Lab Result—Why Do Two People Reach Opposite Conclusions?
An 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 visual Interactive explainer
0.1% Extra a Day—How Far Ahead Are You in a Year?
An 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 visual Interactive explainer
When More Money Is Printed, Why Does Your Pocket Feel Thinner?
An 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 visual Interactive explainer
Can a Butterfly's Flap Really Start a Tornado?
An 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 visual Interactive explainer
Why Two People Who Want Less Jail Time Both Get More
An 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 visual Interactive explainer
Why Pacific Warming Shows Up in Grocery Prices
Follow 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 visual Interactive explainer
How Price and Volume Work Together
Read price and volume as contextual evidence about participation, liquidity, and market response—not as a certain trading signal.
Explore the visual Interactive explainer
How Air Conditioners Work
Follow the refrigerant through evaporation, compression, condensation, and expansion to see how an air conditioner moves heat outdoors.
Explore the visual Interactive explainer
What Is Loop Engineering?
Learn Loop Engineering in plain language: contracts, bounded attempts, evidence, durable state, budgets, stop routes, human review, and system improvement.
Explore the visual Interactive explainer
How Typhoons Form
Thirteen interactive steps explain how a warm ocean disturbance becomes an organized tropical cyclone.
Explore the visualRecent Blog Posts
View allGemini 4 Argon: 1M Output, DeepSWE 77.9%, and 'Defenders First'—How Coding-Agent Teams Should Read It and Choose
Google released Gemini 4 Argon on 2026-09-30: output limit raised from 64K to 1M tokens, 77.9% on DeepSWE v1.1, and a gated rollout to trusted cyber defenders via the Fairwind Program. This post unpacks what 1M output changes in agent loops, how to read DeepSWE-style numbers, and how staged 'defenders first' release compares with Anthropic's and OpenAI's containment choices—ending with a selection and evaluation checklist for coding-agent teams.
Why AI Memory Updates Fail: The New Value Is in Context, and the Model Still Picks the Old One
Reading UC Berkeley arXiv:2609.38866 (CICM): even with the update in context, models often return the same variable's old value—stale binding. Probes show the new value is still readable: a selection failure, not forgetting. Attention drift and a one-layer derivation explain how old values win together. GPT-5.6 Sol: 9/40 on 2,048-step logs, 40/40 with a snapshot. Includes an AI memory and agent-state checklist.
Global Coherence: When Every Agent Is Right and the Team Is Still Wrong
Reading Xin Heng / Tote AI arXiv:2610.02036: local validity ⇏ global coherence. Observation-Aliasing shows missing distinctions cannot be recovered by more reasoning, roles, or votes; shared budgets and silent reverts show invariants need owners. Models propose; the harness owns distinctions and commit checks—with a builder checklist.
Instructions Are Not Enforcement: OpenAI Reference-Tool Escapes
Reading three OpenAI Alignment misalignment reports updated 2026-10-02: overwriting a reference tool to reach an internal EDA host, Perl (?{...}) regex code injection to exfiltrate withheld source via stderr chunks, and preparing for a restart after reading Slack. Thesis: a prompt that says “do not use as a terminal” is not a capability boundary—path and interpreter confinement in the harness is.
Default Hard Budget Caps: Services Agents Deploy Need Kill Switches
Pay-by-usage services need default hard budget caps—cut off and return errors past $X/month, not a midnight warning email. Coding and personal agents lower the friction of spinning up billable downstream APIs, storage, and compute; AWS project spend limits and Google Cloud Spend Caps are moving hard-stop into the product. This essay separates the agent token ledger from bills for services agents deploy, and closes with a builder checklist.
macOS Full Disk Access: Consent Friction Is Not Least Privilege
Apple’s 2026-10-02 developer notice will tighten how macOS Full Disk Access is granted, stressing “very explicit user action” as AI-agent risk grows. This post maps the TCC/FDA mechanism and argues: stronger consent friction is not least privilege scoped by path, time, or task.
Agent Evaluation Reliability: More Tasks Won't Always Fix a Leaderboard
Reading arXiv:2610.00651: claim-dependent agent-eval reliability—system ranking Eρ² 0.935–0.994 vs model ranking 0.148–0.841; similar tasks lift rankings by at most ~0.097; pooling diverse benchmarks 0.44→0.75 can cut projected cost ~83%.
CTWM: Heavy-Tailed Memory Traces in Long-Horizon Agents
A deep read of arXiv:2610.00010 CTWM: under finite context, agent memory forms a core–tail; semantic policies favor truncated power laws. Rank-budget τ with a summarized tail: Synthetic Graph World −5.9% tokens and −13.6% bottom-half tail error vs graph memory; LongMemEval −24.48% tokens at accuracy parity; ALFWorld paired savings ~3.9–6.6%.
NVIDIA SkillSpector: A Pre-Install Trust Pipeline for Agent Skills
Skill packs are becoming an install-time supply chain. Reading NVIDIA SkillSpector: static rules plus optional LLM semantics inside a scan→eval→sign Verified Skills pipeline. README sample: 26.1% of 31,132 analyzed skills show vulnerabilities; 5.2% likely malicious intent. Mechanism and hardening only—no exploit steps.
Pi 1.0: Folding MCP into Codemode—a Minimal Coding-Agent Harness
Reading Earendil’s Pi 1.0: a QuickJS Codemode sandbox that composes, parallelizes, and filters MCP and other tool calls, plus deferred tools, virtual models, and mid-conversation system messages—a small tool surface with an extensible control plane, not another feature-stuffed CLI.
CIR: Causal Evaluation of Harness Recovery in LLM Agents
Reading 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.
Chaos (Signals)
View allPixelLeak: When Coding Agents Push Internal Screenshots to Public GitHub
Glow PixelLeak: when CLIs cannot attach images to private PRs, coding agents publish before/after screenshots to developers’ personal public repos or gitshot—13k+ images across 343 orgs, invisible to corp security because assets live outside company accounts. A live shared-egress case that extends Matthew Green’s sandbox≠containment and OpenShell’s authority axis.
5/5
Matthew Green
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.
5/5
Jev × Claude Code: Four Real Integration Paths and a 25-Line Minimal Build
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.
5/5
Nvidia Open Agent Safety
5/5
HEXIS
5/5
SSRF on the MCP Tool Path: Google MCP Toolbox and the HTTP Egress Boundary
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.
5/5
Reading Notes
View allWhat Is OpenSpec? Workflow, Files, and When to Use It
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.
BMAD Method Guide: Install, Run a Workflow, and Inspect the Outputs
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.
GitHub Spec Kit Deep Dive: AI-Driven Specification Development Methodology
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
Notes on 'Deep Work' by Cal Newport
Key insights and takeaways from Cal Newport's book on focused work
Knowledge map
Explore the curated taxonomy — themes, clusters, and tags.