01Log
Archive
The full log, newest first.
MIMESIS: Learning User Simulators as Training Environments for Interactive Agents
Paper proposes learning user simulators as training environments for interactive agents, framing simulated users as a scalable alternative to costly human involvement.
diffsol
Solves ordinary differential equations and semi-explicit differential algebraic equations, helping developers model systems defined in Rust or a DSL.
ruptures
Provides offline change point detection with parametric and non-parametric models so developers can segment non-stationary signals.
regionmask
Creates masks identifying which geospatial region each grid point belongs to, helping developers aggregate climate data over countries or continents.
McCode
Maintains the McStas and McXtrace codes, so developers simulating neutron or x-ray instruments can trace particle behavior.
SCIRun
Rebuilds a visual environment for scientific modeling and simulation so developers can build workflows, though the beta version may be unstable.
I gave Opus 5.5 one prompt and six hours to visualize Invisible Cities
HN thread (261 points / 139 comments): one prompt, six hours, Opus 5.5 on Invisible Cities — a commenter notes they'd once hand-sketched some of the book's cities on an isometric grid, "but not all 55."
Harvard study on AI productivity in software engineering: the average increase from Claude Code is zero
Bluesky post (199♥ / 77🔁): a Harvard study on AI productivity in software engineering found the average increase in productivity from using Claude Code is zero — "for exactly the reasons you'd think." Study PDF linked: fion.ac/jellyfish.pdf
Cursor: Opus 5.5 is Experiencing 429s
Service degradation with Opus 5.5 across all product components — incident lists Automations, Review Agents, and CLI as affected. Investigating from 13:54 UTC, fix implemented 14:08 UTC, resolved 15:31 UTC on Oct 08, 2026.
OpenAI annualised revenues $20B less than previously signalled
CNBC report that OpenAI's annualised revenues are $20B less than previously signalled — 429 points and 300 comments on HN, the day's biggest thread.
OMP 18.7.0 — interrupted-run recovery and GPT-6 Astra billing fixes
Interrupted runs now emit assistant message boundaries reliably, so subscribers can persist and recover the interrupted turn. Also fixes GPT-6 Astra premium-rate accounting (6× on the OpenAI API, 8× included usage on Codex, counted toward the premium-request limit), adds getOAuthCredentialProvider() for login aliases like openai-codex-device, and patches Vertex AI auth on Windows and Cursor account selection by email.
Local sandboxing for GitHub Copilot now generally available
Local sandboxing for GitHub Copilot is now generally available in GitHub Copilot CLI — Copilot sessions can run with sandboxed execution on the local machine.
Augment Code's next chapter
Worth reading
@jwherrman.bsky.social: A lot of AI assistants seem to have been built around the assumption that the rest of the world is not actually real
John Herrman: "A lot of AI assistants seem to have been built around the assumption that the rest of the world is not actually real," linking to a New York Magazine piece on the AI agent flood.
BitChord
A modern YouTube Music client with clean aesthetics, offering developers a Kotlin-based alternative with features like Hi-Res lossless audio and crossfade.
DroidDeck
A Kotlin project that brings the SteamOS experience to Android, enabling developers to run Steam client and Windows games on Adreno handhelds.
OpenDots
An open-source template for building persistent AI agents that operate across text, calls, and Slack, useful for developers creating always-on AI coworkers.
OpenClaw 2026.9.9
• OpenClaw v2026.9.9: 185 commits · 112 pull requests · 92 contributors. • Release notes and changelog contain the same content, presented in two formats. • Release notes are formatted for people, with expandable sections.
Ghostline
Ghostline is a Go-based Windows app that encrypts DNS traffic and bypasses DPI via zapret2 or GoodbyeDPI.
Crest
Crest is a Swift open source browser for Mac, iPhone, and iPad that separates work, home, research, and private browsing into isolated Spaces.
Hushfacebook
HushFacebook is a Java Morphe patch bundle for Android that removes ads and suggested posts from Facebook 581.0.0.45.58 while adding video saving.
starling
Starling is a JavaScript end-to-end encrypted location-sharing service with no accounts or tracking, now available on Android via F-Droid.
Snitch
Snitch is a Python real-time network traffic visualizer that shows every connection your computer makes, which app is responsible.
OpenAI Withdraws 3 Math Papers
OpenAI withdraws three math papers — the HN thread is at 342 points but flagged as a duplicate, with comments moved to a separate discussion.
OpenAI withdraws three mathematical results
HN thread (379 points, 609 comments) on OpenAI withdrawing three mathematical results, per the openai/math history.md; top comment asks whether the withdrawn proofs were the ones without Lean verification.
DecepEval: A Benchmark for Evaluating Deception in LLM Agents
Asks when LLM agents become more likely to deceive, and introduces a benchmark for evaluating deception in LLM agents.
WebFovea: When the Model Is Right but the Click Is Wrong -- Reliable Round Trips for Vision-Based Web Agents on Live Websites
On the failure mode where a vision-based web agent's model picks the right element but the click lands wrong — reliable round trips for agents running on live websites.
Copilot: Purpose-built model for leaked secret detection
Purpose-built model for leaked secret detection — AI-detected alerts remain included with Secret Protection; the changelog entry includes a billing notice and availability details.
Kiro CLI 2.28.0 — Switch to 3.0 from Classic, Category-Based Hook Matching, and Steadier V3 Sessions
Kiro CLI 2.28.0 offers Classic users a path to switch an interactive session to 3.0 without leaving the terminal; V3 Hooks match by tool category, and long V3 sessions get reliability improvements.
Claude Haiku 5.5
Anthropic's Haiku 5.5 announcement draws 630 points and 318 comments on HN; Simon Willison posts pelicans-riding-bicycles SVG renders across the thinking levels — low messes up the bicycle frame, medium/high/xhigh/max don't.
GPT‑6 and Intelligent UI for everyone
OpenAI's GPT-6 and Intelligent UI announcement pulls 466 points and 235 comments on HN; commenters are comparing 5.6-vs-6 outputs and the redesigned interface.
A Closer Look at Agentic BBO: Benchmarking LLM Agents for Black-Box Optimization
Introduces AgenticBBO-Bench, a unified benchmark for LLM agents on black-box optimization tasks.
Iris 3B
Small enough to run on your own hardware for asset generation when you would rather not call a hosted image API.
AgentGarten: Code Worlds for Evolving Agents
Agents learn through interaction, and what they can learn is bounded by the environments they learn in — AgentGarten's answer is code worlds built for evolving agents.
Step 5 Preview
A flagship agentic model aimed at long-horizon tool use and multi-step workflows.
Claude Haiku 5.5 in GitHub Copilot
Worth reading
Understanding and Enhancing Backdoor Persistency in LLM Agent Post-Training
Asks whether benign post-training can remove inherited backdoors in LLM agents, and examines how persistent those backdoors remain — security reading for anyone fine-tuning or sourcing agent models.
CheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers?
Introduces an executable benchmark for evaluating whether long-horizon agents can synthesize static-analysis checkers — a concrete yardstick for coding-agent evals on extended, multi-step work.
Beam
A tiny, teachable WebGPU library that exposes the real WebGPU API through five nouns and two verbs with first-class TypeScript types.
Viewi
A front-end framework that compiles PHP components into reactive browser apps, worth exploring if you want to build interactive web UIs without leaving PHP.