Search stories, models, companies…
Subscribe

Popular topics

OpenAI83Anthropic81Google Gemini45Claude Code27Coding agents51Model Context Protocol (MCP)13
The week in AI, in one email.
Topic · Product

Claude Code

Claude Code is Anthropic's agentic coding tool: it reads a codebase, edits files, runs commands and works with git, using Claude models. It started as a terminal tool in February 2025 and now runs in IDEs, a desktop app and the browser, making it one of the main reference products for coding agents.

27 stories · updated Oct 27
Follow via RSSGet Claude Code alerts

Key facts

Checked Oct 8
General availability
May 22, 2025 (with Claude 4)

Start here

Developers · GuideHow to write a CLAUDE.md or AGENTS.md file that coding agents actually followWhere each agent looks for its instructions, how long the file should be, what to put in it, and how to check the agent is reading it, from Claude Code, Codex, Cursor and Copilot docs.·10 min read
Agents · ExplainerClaude Code mods, explained: what Anthropic's new extension layer can do, where it runs, and the security trade-offSince October 1, 2026, Claude Code can load JavaScript and TypeScript 'mods' that redraw its interface, rewrite prompts and approve tool calls. What Anthropic's docs say they can do, and what they can reach.·8 min read
Developers · ExplainerClaude Code review, explained: how Anthropic's Claude Code team reviews AI-written code, and the /code-review, ultrareview and Code Review tools you can useOn October 15, 2026, Anthropic described how the Claude Code team does code review when Claude writes about 90% of the code: parallel AI reviewers, risk-based human approvals and fast reverts. Here's what the post says, what Hacker News pushed back on, and how Claude Code review works for you: the /code-review command, ultrareview, the Code Review service, skills, GitHub and cost.·11 min read

Latest on Claude Code

Developers · ExplainerWhat is context engineering? How it differs from prompt engineering, and where the practice stands in October 2026What is context engineering? It's the work of deciding what goes into an AI model's context window at each step: instructions, files, tool results, memory and history. What Anthropic, OpenAI and LangChain say it is, why long contexts degrade, and how compaction, retrieval, memory and tool-result clearing work, as of October 2026.·9 min readProducts · ExplainerWhy is my Claude usage going so fast? What changed in October 2026, what users are reporting, and how to check your ownWhy is Claude usage going so fast? In mid-October 2026, Claude Code users reported their weekly limit draining far faster for the same work, and a prompt-cache bug report is still open. What's confirmed, what's only reported, and how to check your own usage.·10 min readDevelopers · GuideClaude auto mode is now the default: what it does, how it differs from accept edits and bypass permissions, and how to turn it offClaude auto mode has been Claude Code's default since August 14, 2026, and on October 22 Anthropic said Claude's web, desktop and mobile apps will follow. How the classifier works, how it compares with accept edits and bypass permissions, and how to switch back to manual.·9 min readProducts · GuideIs Claude free? What the free plan includes in October 2026, its limits, and when Pro is worth itIs Claude free? Yes: as of October 23, 2026, Anthropic's free plan includes chat with Sonnet and Haiku, web search, memory, connectors, and Claude Docs, Slides and Design. It doesn't include Opus, Claude Code or Research, and Pro costs $20 a month.·7 min readAgents · AnalysisShipping AI-written code you don't understand: what the evidence says about 'comprehension debt', and what teams are doing about itShipping AI-written code you don't understand is now a mainstream worry, with an October 19, 2026 Ask HN thread drawing hundreds of replies. Here's what studies from Harvard, METR, Anthropic, Stack Overflow and DORA actually measured, what cases like PostgreSQL 19 show, and which review rules the official tools and projects document.·9 min readDevelopers · ExplainerClaude Code review, explained: how Anthropic's Claude Code team reviews AI-written code, and the /code-review, ultrareview and Code Review tools you can useOn October 15, 2026, Anthropic described how the Claude Code team does code review when Claude writes about 90% of the code: parallel AI reviewers, risk-based human approvals and fast reverts. Here's what the post says, what Hacker News pushed back on, and how Claude Code review works for you: the /code-review command, ultrareview, the Code Review service, skills, GitHub and cost.·11 min readDevelopers · AnalysisQGIS bans AI-assisted code: which open-source projects ban AI contributions, and whyQGIS now rejects any AI-, LLM- or agent-assisted code in its main repository. It joins Gentoo, NetBSD, QEMU and Servo among open-source projects banning AI contributions, while LLVM, curl, llama.cpp and the Linux kernel allow AI help with disclosure. Here's what each policy says and the reasons behind it.·9 min readAgents · AnalysisIs AI a tool? Rich Hickey's "'AI' Is Not a Tool" vs "AI is a tool and using it well takes skill," and what the evidence saysIn October 2026, Clojure creator Rich Hickey argued that LLMs are automation, not tools. A same-week reply argued that AI is a tool and using it well takes skill. Both essays, side by side, and what recent evidence on coding agents does and doesn't settle.·7 min readIndustry · NewsAccenture caps central Claude funding at $29 a month per employee, 404 Media reports. Why agentic AI blows up per-seat budgetsAccenture now centrally funds only $29 a month of Claude usage per employee, according to an internal announcement seen by 404 Media on October 15, 2026. Some staff said they spend $500 to $1,000 a month. The Accenture Claude spending cap shows why agentic coding breaks per-seat AI budgets.·5 min readDevelopers · NewsAnthropic Scion: the in-house source control system that replaced Git for its monorepo (and why it isn't open source)On October 13, 2026, Anthropic described Scion, a version control system it built to replace Git for its monorepo after daily merges grew from about 2,500 in May to more than 30,000 in September. Despite some reports, Scion isn't open source: Anthropic says it isn't a general replacement for Git and is sharing the ideas instead.·6 min read

Nothing in this format on this page — try another filter or the next page.