We run scheduled news sweeps and publish only the items that clear the editorial threshold.
Alderson applies web-performance habits to agent workflows. He argues that inference speed is only part of it: with provisioning, tools and suspend and resume unchanged, he says halving inference time takes about 20% off a task, a figure he…
The author of the nullprogram blog released Prospero, a coding harness written in C++ with a Dear ImGui interface. It includes no model providers.
The help article says "The Max 20x plan is now called the Ultra plan." Existing subscribers move over automatically at no price change. Ultra costs $200 a month and includes Claude Code.
Wiz lists Fireworks AI (Oct 6), Andromeda (Oct 9), Zeabur (Oct 14), Lightning AI (Oct 15), OpenCode (Oct 16 to 17), Railway (Oct 20), Warp (Oct 23), CommandCode (Oct 28) and Northflank (Oct 30). It says most of the incidents are still being…
The release notes list a new setting, permissions.blockWritesOutsideWorkingDirectories. With it on, the Write, Edit and NotebookEdit tools refuse paths outside the working directories "in every permission mode." The notes name those three…
Haas writes that PostgreSQL major releases have landed between mid-September and mid-October for a decade, and that 19 is likely to slip to November or later. Three large features were reverted between August 27 and September 15:…
Cursor says a maliciously modified 2.1.313 was live from about 2:27am to 1:35pm PT on October 29 and that at most 5,000 users were affected. Per Cursor, the code collected hostname, username, home directory, environment variable names,…
Jain had coding agents build the same Java backend service ten times per model, with and without a harness of contract specs, examples and deterministic test feedback, then scored every build against 178 external acceptance tests. GPT-6 Sol…
Pandya says he builds an observability tool for long-running AI agents. On October 28 he ran Claude Code 2.1.286 in auto mode with seven background subagents, each closing a GitHub issue in its own git worktree, on macOS with no sandbox.
The repository describes a desktop app for terminals and coding agents that groups work into spaces, lists agents in a sidebar as Working, Blocked, Done or Idle, and keeps terminals running when the window closes. The README also covers SSH…
Laycock describes an internal experiment run by Giles Alexander, Thoughtworks' Regional CTO for Europe. Senior engineers, infrastructure consultants and product people spent a week building an airline application with no code written by…
In Mindustry, a factory-building strategy game, GPT-6.1 Sol agents in Codex beat Claude Opus 5.5 agents in Claude Code 6-1 across seven games over about 9.5 hours. In Bed Wars, 10 agents per side, the GPT team won 6-3 in nine games.
Mistral says it is releasing the weights of its 1-trillion-parameter model. It reports 41% on Terminal-Bench 4.0 (up 13 points from the preview), 19.7% on Cognition's private FrontierCode 2.0, and a 48% score on the Artificial Analysis…
The Zig Embedded Group's code of conduct now carries a "Strict No LLM / No AI Policy" covering its GitHub organization and Discord server. It rules out LLM-generated code or prose, paraphrasing LLM output, LLMs for editing "including fixing…
The reporter says Claude Code adds a "# userEmail" block, "The user's email address is ...", to every session. They say the value comes from the OAuth account in ~/.claude.json, that no setting turns it off, and that IS_DEMO=1 hides the…
Google's notice says Jules will wind down on December 31, 2026, "as part of our work to unify our agentic coding efforts." Users have until November 11 to finish sessions, after which Jules becomes read-only through the end of the year.…
Meta says its Catching Just-in-Time Tests system is now part of its infrastructure. It runs overnight on spare capacity against the previous day's diffs that a risk model flags.
The authors ran 1,886 npm releases of Claude Code, Codex, Gemini CLI, Qwen Code and OpenCode in sandboxes, sent each the same prompt, and recorded the first request each agent made to its main model. They call everything the agent adds…
Flamerix AI reports that Claude Code sends each active background agent's full transcript to that agent's own model about every 30 seconds and asks it to "describe your most recent action in 3-5 words". The answer only updates a status…
Funnel randomly assigned each new task in Reef, its internal data agent, to either GLM-5.2 (open weights) or Claude Opus 4.8. GLM averaged 7.8 seconds per model call against 18.1 for Opus.