Coding
Torvalds uses Claude Code to rework the Linux page cache
Linus Torvalds posted eight Linux kernel patches made with Claude Code. On his laptop, 8-thread small reads used about 4x fewer CPU cycles each.
AI Coding news and analysis
AI coding news: editor agents that finish pull requests, labs cutting model access to tools like Cursor, surveys of how much code agents write, rewrites done with AI help, and model-written machine-checked proofs. Each story gives the figures, dates and caveats about the resulting code.
Dev Stack
VS Code 1.141 sandboxes AI agents on Windows, macOS, Linux
VS Code 1.141 sandboxes AI agents on Windows, macOS and Linux, shows agent sessions in a grid and picks up Codex and Copilot chats started in other apps.
Dev Stack
GitHub stacked pull requests are now generally available
GitHub made stacked pull requests generally available on October 6, 2026, on every github.com plan, with stack-aware merge queues and the gh stack CLI.
Dev Stack
Atlassian puts OpenAI models inside Rovo and Jira
Atlassian and OpenAI expanded their partnership: OpenAI models now power Rovo, and ChatGPT and Codex reach Jira through an MCP server that takes 15M calls a day.
AI & LLMs
Reflection AI launches Beam, a 501B open-weight model
Reflection AI's Beam has 501B parameters but uses 23B per token, scores 80.9 on SWE-Bench Verified, and ships weights under Apache 2.0 later in October.
AI & LLMs
HackerRank launches Chakra, an AI interviewer for coders
HackerRank's Chakra watches developers code in a live repository, lets them use AI and asks follow-up questions. It ran 500,000 interviews before launch.
Dev Stack
Capcom REX plans an AI-ready rebuild of its RE Engine
Capcom unveiled REX on October 2, a staged plan to turn RE Engine, used on 27+ games, into an AI-ready engine. Two of its parts are going open source.
Dev Stack
Claude Code 2.1.287 adds Claude Mods for deeper plugins
Claude Code 2.1.287, out October 1, lets plugins change the agent's deeper behavior through Claude Mods and adds an opt-in side agent that flags mistakes.
AI & LLMs
Gemini 4 Argon opens to cyber defenders before developers
Gemini 4 Argon scores 77.9% on DeepSWE v1.1 and can write 1M tokens per answer, but only cyber defenders in Google's Fairwind Program can use it so far.
Coding
Rails World 2026: DHH says hand-written code is obsolete
DHH says he wrote 150,000 lines of code in August 2026 alone, versus 30,000 a year by hand, as 37signals rewrites Hey's mail server in Rust.
Dev Stack
Claude Code AGENTS.md support needs telemetry turned on
Claude Code 2.1.277's AGENTS.md support sits behind a remote feature flag, so it silently stops working when telemetry is off, a GitHub issue shows.
AI & LLMs
GPT-6 Astra breaks an Enigma message unsolved since 2005
OpenAI's GPT-6 Astra recovered the key to an 82-letter German Army Enigma message from 1941 that had stayed unsolved for 21 years.
Dev Stack
Claude Code 2.1.277 reads AGENTS.md as a fallback
Claude Code 2.1.277 reads AGENTS.md when a project has no CLAUDE.md. Over 60,000 open-source projects already ship that file.
Dev Stack
ZCode uploaded whole Git histories; Zhipu apologizes
One snapshot reached 313MB and 42,411 files, and 86.6% of it was the .git directory, sent to cloud storage the user cannot decrypt.
Dev Stack
Linux 7.4 kbuild patches cut kernel build times
A kbuild series aimed at Linux 7.4 cuts no-op builds by roughly 80% and trims 37.6 seconds off a full allmodconfig rebuild.
Coding
Shopify drops React Native for Swift and Kotlin
Shopify is rebuilding its apps in Swift and Kotlin 6 years after going all-in on React Native. Coding agents did enough of the porting to change the math.
Dev Stack
VS Code 1.136 adds Agent Merge to finish pull requests
VS Code 1.136 ships Agent Merge in preview. An agent answers review comments, fixes failing checks and resolves conflicts until a pull request is ready.
Coding
Anthropic's AI formalizes Fermat's Last Theorem in Lean
Anthropic says an internal model wrote 13 million lines of Lean in 11 days, producing a complete machine-checked proof of Fermat's Last Theorem.
Dev Stack
OpenAI will cut Cursor off from its models on November 12
OpenAI is ending Cursor's direct model access on November 12, 2026, after SpaceX bought Cursor's parent Anysphere for about $60 billion on August 14.
Coding
JetBrains: developers say agents now write 47% of their code
A JetBrains survey of 15,509 developers finds agents fully write 47% of code on average. 90% use an agent weekly, and Claude Code leads adoption at 39%.
Dev Stack
Bun 1.4 ships the AI-driven Rust rewrite to production
Bun 1.4 is the first production release of the runtime's Zig-to-Rust rewrite, shipping faster startup and new APIs while critics question 13,044 unsafe blocks.
The weekly digest
One email every Friday with the week's top stories from all six desks: AI, dev tools, coding, the tech industry, startups and what's next. Free, no spam.