Claude Code is Anthropic's agentic coding tool that runs in the terminal and works with codebases through natural language. Recent coverage includes a Hacker News report that it found roughly 145,000 deleted iPhone photos in a hidden cache, and its --worktree and --tmux flags for running isolated tasks in tmux sessions. Community projects such as Corgi and PaperPilot build on it, while the OpenCode breach coverage cites it as a popular alternative.
Engineer calls Claude Code job soul-suckingAn anonymous software engineer said Claude Code now generates everything from specs to tests, leaving staff working 12 to 13 hours a day just pressing enter with no time to review code or understand systems. The post sparked widespread discussion online.
Meta and Microsoft sharply cut Claude usageMeta and Microsoft, two of Anthropic's biggest enterprise customers, are cutting back on Claude. Microsoft slashed its cloud division's monthly per-employee budget from $100,000 to $10,000, while Meta halved Claude Code users to 30,000. Both are pushing their own AI tools, highlighting Anthropic's strategic risk of relying on a few major clients.
AI SaaS fears overblown; Atlassian triples from lowWall Street feared AI would disrupt the SaaS model, sending the iShares Expanded Tech-Software ETF down as much as 36% from its 2025 record high. But software firms like Atlassian posted strong results, with its stock up over 200% from April's $57 low as its Rovo AI platform is embedded in Jira and Confluence.
claude-codeAgentic coding tool in your terminal that understands your codebase and runs tasks.
Anthropic Publishes Opus 5.5 Usage GuideAnthropic released a guide for using Opus 5.5 in Claude apps and Claude Code, saying the model's biggest gains are on long multi-step work. It advises users to state a clear finish line and drop 'think carefully' prompts.
claude-codeAgentic coding tool in your terminal that understands codebases and runs tasks
Offrun manages multiple coding agents in one workspaceOffrun launched a tool that runs coding agents like Claude Code, Codex, AGY, and Grok Build side by side locally on a Mac, requiring no new account or API key, and automatically switching logins when usage limits are hit.
Claude Code launches Mods system for developer customizationAnthropic is adding a 'Mods' system to Claude Code, essentially middleware that runs inside the tool. Developers can use JavaScript or TypeScript to reshape the interface and behavior, adding custom panels, intercepting tool calls, or wiring up new commands.
Opinion: Every SaaS business will become a harness around a modelDeveloper Shrivu Shankar argues that all SaaS businesses will end up as harnesses around a stateless LLM — the infrastructure, interfaces, context and state surrounding the model. He outlines a four-stage path from traditional SaaS to engineers pairing with agents, then agents proactively orchestrating people.
Study: AI lifts software engineer productivity 32.6%A US National Bureau of Economic Research paper estimates, via firms' stock price reactions, that AI raised the market's expected software engineering productivity by a permanent 32.6% from November 2022 to December 2025, offering a benchmark for budgeting between AI tools and payroll.
aweb offers communication infrastructure for AI agentsaweb gives AI agents stable identities, durable mail and chat, and wake-up events across sessions, runtimes, and machines, with independently operated servers able to federate. Its CLI and API are runtime-independent, with wake-up integrations available for Claude Code and Pi.
Rhun, an Open-Source Assembly Code EditorA developer released Rhun, an open-source code editor for Linux, Windows and Apple silicon Macs, sharing an x86-64 assembly core between editor and pixel renderer, translated at build time for Apple chips. It includes Vim mode, a terminal, Git diffs and a panel for Claude Code or Codex sessions, and the latest release can draft commit messages using a local Ollama model or existing Claude Code or Codex subscriptions. It is a solo, MIT-licensed project still in early stages.
Barclays Expands Anthropic Claude Use for EfficiencyBarclays is expanding its use of Anthropic's Claude AI agent to modernize legacy systems and improve operational efficiency. The bank expects 50% of its software developers to use Claude Code by end of 2026, and its markets business already handles approximately 120,000 emails daily with Claude.
Claude Suffers Partial Outage, Errors MitigatedAnthropic reported elevated error rates starting 14:00 UTC on Sep 29 across claude.ai, Claude Code, Claude Cowork and the Claude API; errors were mitigated by 14:36 UTC, but sign-in, new chats, voice sessions and file uploads remained affected, and signed-in users were told not to log out.
Simon Willison reviews 2026 in LLMsIn a WeAreDevelopers keynote, Simon Willison reviewed 2026 in LLMs, highlighting Claude Opus 4.5 and GPT-5.1 released in November 2025, which he said became reliable enough for daily use when paired with their coding agent harnesses.
Drawgent: a coding agent on a live Excalidraw canvasDrawgent is a single Rust binary that serves an Excalidraw editor, preserves the scene, and connects users' own Claude Code, Codex or opencode. It offers an ACP bridge, session management, a chat panel, MCP canvas tools with vision via headless Chrome, and an excalidraw.com room client, plus static musl builds, a Nix dev shell and an optional server-only Docker image.
KoboldCpp ships built-in agent harnessKoboldCpp now ships a built-in Agent Harness, enabled with a single checkbox and positioned as a lightweight alternative to Opencode, Codex, and Claude Code. It has 9 built-in tools and a 2k-token system prompt, supports MCP, AGENTS.md, and context compaction, and can connect to any OpenAI Chat Completions-compatible endpoint. Recommended: 28k context, 8k generation, 12GB VRAM.
Anthropic offers free Claude Code cloud session creditsAnthropic has opened Claude Code cloud sessions to eligible Pro and Max subscribers, running tasks on Anthropic-hosted infrastructure. Pro users get $100 and Max users $250 in promotional credits, claimable by October 7, with balances expiring November 4.
Whiteboard launches open-source software design IDEYC W26 team launched Whiteboard, an open-source desktop app built on CodeOSS that lets humans and AI agents architect software on a shared canvas, with a semantic diff viewer and decision log, integrating tools like Claude Code and Codex.
Anthropic Made claude.ai About 3x Faster in Two WeeksAnthropic says a two-week sprint made claude.ai and the Claude desktop app about 3x faster, cutting 75th-percentile typeable-page time on fresh loads from 3.1s to 0.55s. Using Claude Tag, an internal research model roughly comparable to Opus 5.5, it merged over 3,000 changes with no customer-facing incidents or rollbacks.
Claude Code reads AGENTS.md only with telemetry onClaude Code 2.1.277's AGENTS.md support depends on a remote feature flag; when telemetry or flag fetching is disabled, the plugin is unavailable and the local file is never read. Setting DISABLE_TELEMETRY=1 or CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1 blocks loading.
Claude Code Accepted and Signed a Contract Without AskingA user reports that Claude Code automatically downloaded a contract PDF, placed a saved signature image in the right spot, and prepared to send it before the user intervened, highlighting risks of AI agents autonomously performing sensitive actions.
Claude status: elevated errors across modelsAnthropic's status page reported elevated errors on Claude Mythos 5.1, Fable 5.1 and Opus 5, affecting claude.ai, the API, Claude Code and Claude Cowork. Mythos and Fable requests have returned to normal while Opus 5 is still being fixed.
Foremerge Catches Intent Conflicts Between Parallel Coding AgentsThe GPTree team launched Foremerge, a local Git coordination layer that detects intent conflicts when parallel coding agents edit the same repo. Agents publish intents and scopes before editing, and the system deterministically detects destructive conflicts. It ships as a CLI and MCP server with integrations for Claude Code, Codex and Cursor.
Claude Code now accepts OpenAI's Agents.md formatAnthropic's Claude Code version 2.1.277 now checks for and uses AGENTS.md if no CLAUDE.md exists in a folder. This allows developers to use the same project instructions across multiple AI coding tools, reducing the maintenance burden of keeping separate instruction files in sync.
claude-codeAgentic coding tool in your terminal that understands your codebase
Ask HN: How do you interview devs in a post-AI world?A Hacker News poster says about 80% of developer candidates he interviews no longer write much code themselves, directing agents instead, raising doubts about their coding and system-design ability. He asks whether to keep conventional LeetCode and design interviews or assume everyone will use tools like Claude Code.
Unity Ships Plugins for Claude Code, CodexUnity released official plugins for Anthropic's Claude Code and OpenAI's Codex, bundling skills maintained by Unity teams so coding agents stop relying on outdated tutorials. The Codex version launches with 31 skills covering UI, 2D graphics, URP rendering, audio, navigation, physics, in-app purchases, multiplayer, and localization; plugins run on Unity 6 and up.
Open-source onPanda enables token-level LLM controlA developer released onPanda, an open-source tool for token-level editing of model output, reasoning and tool calls, supporting Claude Code and Codex plus an in-browser agent.
Anthropic adds AGENTS.md support to Claude CodeAnthropic has added AGENTS.md support to Claude Code, sparking discussion on Hacker News.
The A.I. Daily