01Log
Archive
The full log, newest first.
NanoClaw 2026.10.0
First calendar-versioned release; /update-nanoclaw now installs published releases instead of the tip of main. Breaking: OneCLI installs must upgrade the OneCLI gateway to exactly 1.42.0 first β it closes a credential-injection bypass, and /update-nanoclaw never upgrades a running gateway.
Anthropic: 2026 usage policy update
Anthropic published its annual Usage Policy update on Oct 8, 2026; the post summarizes the changes.
Kiro β Memory Across Chat Sessions
Kiro changelog β memory across chat sessions, so context carries between sessions.
FinanceHarness
An autonomous financial research framework that gathers evidence, performs valuation and risk calculations.
openctp
Provides CTPAPI-compatible interfaces for multiple Chinese brokerage trading gateways and a 24/7 simulation environment covering futures, A-shares, funds.
TradingChart
Native SwiftUI trading charts for iOS featuring candlesticks, technical indicators, crosshairs, drawing tools.
northstar
An open-source quantitative trading platform supporting strategy research, historical replay, and automated trading for futures, stocks, forex, and crypto.
easy-stockοΌAθ‘ AI ζΊθ½ζη ε·₯δ½ε°
An AI-native desktop workbench for A-share market analysis that aggregates sources, structures themes and sentiment data.
Five months treating bugs like patients and coding agents like a medical team
Cockroach Labs writes up five months running coding agents as a medical team for bug triage β the piece says it consumed just over $135,000 in Claude tokens; 197 points / 94 comments on HN.
AutoHarness
Builds a self-learning skill layer for Claude Code that distills, updates, and prunes skills from real sessions to improve performance.
iPhone Use
Enables Codex to control physical iPhones via USB using WebDriverAgent for app automation with real-time screen display and screenshot fallback.
Intent-Router
Compiles vague agent requests into typed IntentSpec contracts that probe, ask, or halt before routing to ensure inputs are unambiguous.
rea
Reverse engineers software from app behavior down to native binaries using AI agents to trace functionality to the binary level.
LiteLLM
Routes 100+ LLM APIs through one OpenAI-format gateway with cost tracking, guardrails, and load balancing to simplify multi-provider integration.
Iranian campaign planted fake articles in real U.S. publications using ChatGPT
Washington Post report that an Iranian campaign planted fake articles in real U.S. publications using ChatGPT β 191 points and 172 comments on HN, with OpenAI's Thursday response quoted in the thread.
Omarchy Apple Dev
This Python project builds and deploys iOS apps from Omarchy Linux without Xcode, and developers look at it to run SwiftUI code on physical iPhones using Linux.
perfetto
Perfetto is a C++ suite for tracing and profiling complex systems, and developers look at it as the production-grade default system for Android and Chromium.
T3 Code
T3 Code is a TypeScript control surface for AI agents on your machine via mobile, web, and Electron apps, worth viewing to manage your local Claude.
Mural
Mural is a native TypeScript iPhone and Android app for learning languages through conversation, useful to examine for its implementation using OpenAI.
Backburner
Backburner is a Python tool that uses a USB-C cable to help a Mac run a 27B model with an iPhone, allowing faster prompt reading and more context.
Mxc: Microsoft Execution Containers version 1.0.0
Microsoft Execution Containers reaches version 1.0.0 β 151 points and 33 comments on HN, where the top comment calls it 'finally answering bubblewrap' and takes up the industry's permissioning record.
RoboQuest: Generalist Physical Agents that Search, Inspect and Test
A benchmark for goal-directed embodied exploration β generalist physical agents that search, inspect and test. Physical-agent eval rather than coding-agent, but squarely agent-benchmark research.
LegalOn halves Codex costs while maintaining development speed
OpenAI customer story on Codex in production: LegalOn halves costs while maintaining development speed β a concrete cost-outcome data point for coding-agent deployments.
From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation
Proposes agentic language world models β interactive environment simulators built from traces, letting agents run in simulated worlds; relevant to anyone building agent training or eval environments.
Cursor: Elevated errors affecting Opus 5.5 β resolved
Service degradation affecting Opus 5.5: users saw intermittent errors or failed requests across Automations, CLI, Cloud Agents, IDE, and Grok Bot. Investigating posted 19:52 UTC, resolved 20:51 UTC on Oct 08.
Kiro CLI 2.29.0
Release feed lists 2.29.0 (Oct 16); the changelog's 2.28.0 entry (Oct 5, 2026) switches an interactive Classic session to 3.0, matches V3 Hooks by tool category, and improves reliability in long V3 sessions.
Codex 0.162.0
Adds tools for creating and listing managed Git worktrees from trusted local projects when the worktrees feature is enabled, plus configurable live web access and remote compaction for custom Responses-compatible model providers; Code Mode gets opt-in ranked tool search.
Why isn't the industry freaking out about DeepSeek 4.1 Flash?
347 points and 297 comments on HN. Top comment's explanation for the muted reaction: most people are using heavily subsidized subscriptions.
LightOnOCR 3 0.8B
An image-to-text OCR model you can host yourself, so document extraction pipelines stop round-tripping every page through a hosted vision API.
Youtu-Parsing-Omni
Converts document images straight into structured text, so parsing can live inside a multimodal pipeline instead of a separate OCR stack.
Qwen-Image 2.1 Turbo
A faster cut of the Qwen image line for builders who want generation latency down without leaving the Qwen ecosystem.
Voxtral Mini 4B Realtime Arabic
Gives Arabic voice agents a streaming transcription path instead of forcing batch audio uploads through a hosted API.
Strands Decider 26B A4B
A heavier decider for agent stacks whose routing calls have outgrown what the small variant can resolve.
GPT-6.1 Sol
Sol is the model Asana's browser agent runs on, making it the current reference point for teams wiring web-automation agents into OpenAI's stack.
LIDstral Arabic
A small classifier for tagging Arabic text before it reaches a larger model, useful for routing and filtering pipelines.
Scaling Agentic Data for Long-Horizon Terminal Intelligence
Research on scaling agentic data for long-horizon terminal intelligence β the data side of long-horizon agentic performance.
OpenAI, the Partition Principle, and Mathematics
HN discussion of OpenAI's math releases and the Partition Principle β 211 points, 313 comments. One framing in the thread: it can be true both that OpenAI is 'inconsiderate/harmful' with its math releases and that they have created 'a treasure trove'.
Building effective agent automations
Reference implementation walkthrough of agent automations β covers sources, destination, agent, schedule, memory, and guardrails, plus common failure modes. By Lance Martin and CJ Avilla, 9 min read.
How Oracle turns days of work into minutes with ChatGPT and Codex
OpenAI customer story on Oracle's use of ChatGPT and Codex β headline claim is turning days of work into minutes.
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.