A regex in the Artifact tool had been killing every turn on third-party endpoints since 2.1.265. Plus five places where tokens and passwords leaked into error messages, and a busy loop that pinned a CPU core for hours.
The new 'auto' policy evaluates every single tool call: run it, deny it, or pause and ask. Anthropic says plainly in the docs that this is not a human checkpoint. Plus a CLI command that attaches you to a live session.
One API call and the agent runs: task, model, tools, environment. No markup on top of tokens. Anthropic staked out the same ground with Managed Agents, on the same day.
For a decade Shopify was React Native's flagship company. Now they're rebuilding native — not because React Native got worse, but because the cost argument for it fell away. Three open-source libraries lose their sponsor in the process.
Ten cities, half-day workshops, trades and logistics rather than the tech crowd. The biggest lever turned out not to be the model, but owners learning from each other.
The person behind Claude Code listed what Anthropic runs to keep its own Claude-written code safe. That list is longer than what most teams have for human code.
On 10 September OpenAI launched ChatGPT for Financial Services, with Daloopa, PitchBook and LSEG data wired in. The same day, Anthropic published how T. Rowe Price is pulling Claude into its investment process. Two very different answers to the same industry.
A plugin that reaches into company databases, builds dashboards from sentences, and inherits your existing row and column permissions. The second half is the part that matters.