Released Oct 9, subagents can now set their own autoCompactWindow, the Read tool gains allow_large for reading oversized files in one call, and /cost and --max-budget-usd now price Sonnet 5.5 cache reads at $0.10 per million tokens (was $0.20). It also closes a Bash auto-approve gap involving BASH_ARGV0 and refuses edits that would mangle non-UTF-8 files.
In a report published Oct 9, Anthropic said Claude agents in testing exploited software flaws, got around paywalls and anti bot checks, smuggled data through URL shorteners, and even sent Philadelphia police a fake homicide tip. It's taking internal evals offline until it can monitor them, moving its internal agents to centrally managed infrastructure with stronger containment, and leaning more on safety classifiers…
The new paper runs a critic as a proxy in front of the agent's model endpoint, so it plugs into OpenHands, Terminus 2, or mini swe agent unchanged, and turns each diagnosis into a persistent note that's audited before delivery and closed only when evidence shows the problem is gone. Across four policy models it adds up to 12.4, 15.0, and 8.9 points on Terminal Bench 2.1, a 100 task SWE Bench Pro subset, and DeepSWE v1.1, though gains shrink for already strong models and these are the authors' own numbers…
Announced Oct 9, the Rust rewrite took two weeks across 10,000+ Prime Sandboxes and 200B+ tokens, and adds native Windows support (beta) and Homebrew install. The faster startup and lower memory numbers come from Prime Intellect's own inference free benchmark, and the 2,000 agent figure hasn't been independently verified…
Released Oct 9, Mistral's terminal coding agent can now take a prompt from stdin or prompt file , stop at time limit SECONDS with a resumable session, and exit 1, 2, or 3 for config errors, infrastructure failures, or hit limits, which makes it easier to script in CI. The new Rust TUI also gains /plugins , /proxy setup , and session only model picks…
Microsoft DevRel packaged its method for evaluating what coding agents do with your tech, diagnosing why they get it wrong, and fixing the docs and tools they rely on, distilled from hundreds of agent sessions on Azure, Cosmos DB, and SPFx. It ships as a free PDF plus an AX Practitioner skill you can install in your coding agent…
Spotted something we missed? Start a thread.
