Claude Code's Don't Ask Again Exposed Secrets to GitHub
Apiiro found secrets in 1,122 public copies of Claude Code's settings.local.json, saved by the Don't Ask Again button. What happened and what to do.

Apiiro found secrets in 1,122 public copies of Claude Code's settings.local.json, saved by the Don't Ask Again button. What happened and what to do.

Claude Code's official marketplace now lists an Xcode plugin with Apple Inc. as author, for builds, tests and SwiftUI previews, loaded from your Mac's Xcode.

Goldman Sachs limited Claude Code and GitHub coding tools to engineers. Hacker News argued over security, billing and IPO timing; X posts pushed sandboxes.

Adweek reports Anthropic signed its first paid content deal with a news publisher, the Associated Press, just before the midterms. Neither side has confirmed it.

Anthropic's FlashProve proves which model answered a request, at 70 to 95 times the GPU time. Hacker News asked who needs it and what it costs; X focused on cost and correctness.

Claude Code 2.1.317 changes the rule against recreating existing games: you can now name a game to describe mechanics, and Claude should build an original one.

Anthropic added 14 agents and products to Claude Marketplace on Nov 4, from Chainguard to Zoom. Eligible customers can pay with committed Anthropic spend.

Anthropic's biology lab says Claude helped find, purify and map a 96-copy phage vault in under four months. Function is still unknown and the preprint is pending.

Cat Wu, who led product for Claude Code and Cowork at Anthropic, is joining OpenAI to lead Core Products PM. OpenAI confirmed it, per Business Insider.

A judge dismissed the direct infringement claim against Dario Amodei with leave to amend and left Anthropic's motion open in the music publishers' lyrics case.

Claude's invisible text watermark now covers Mythos 5, Opus 4.7 and Sonnet 4.6, with older models reported for Nov 16. What it can and cannot prove.

Claude's message threads beta lets agents send only new messages each turn. Threads expire 5 minutes after the last request; zero data retention is excluded.

Anthropic's owners include its seven co-founders, employees, investors, Amazon and Google. A trust and a founders' LLC control the votes, per its October 2026 S-1.

The Model Context Protocol (MCP) is an open standard for connecting AI apps like Claude and ChatGPT to files, databases and tools. Here is how hosts, clients and servers work, what tools, resources and prompts are, who runs MCP, and what to watch for.

Claude users say Anthropic banned them right after Persona ID checks with Russian passports, even in supported countries. What the rules say.

YC Labs and Olam Labs ran swarms of GPT-6.1 Sol and Claude Opus 5.5 agents in Minecraft and Mindustry. Commenters on X and Hacker News joked about the agent bureaucracy, questioned the roster-order hierarchy, and pushed back on the source code headline.

Nvidia is in talks to guarantee Nscale debt for a 460MW West Virginia data center that Anthropic plans to use, The Information reports. Nothing is signed.

Anthropic's own Claude API now takes 128 MB Messages requests, up from 32 MB. Bedrock and Google Cloud have lower limits. A cost analytics API is in beta.

WIRED's sources say an Accenture worker's personal Claude Code agent ran on a DOD network for two months and appears to have sent out logins.

Anthropic trained Claude to check each conversation for misuse right after it replies. It flags 94% of high-priority cases for under 2% extra compute.
