Boris Cherny

Theorem Labs, the firm behind the formal models in Anthropic's 123-library verification project, now offers OSS Verify: free, AI-written Rocq proofs that a project's fuzz targets never crash. Here is what is proved, who qualifies, how to enroll and what the fine print says.

Anthropic's Frontier Red Team says LLMs are making formal software verification feasible at a much larger scale. Claude proved no-crash properties for 239 entry points across 123 open-source libraries, at the RISC-V binary level, in a few weeks. explainx.ai walks through the method, the numbers, the bugs and the limits.

On October 21, 2026, Anthropic opened a research preview of Claude Duet, a standalone app where Claude works as a proactive agent. It sends a morning brief, checks your apps every few hours, takes on tasks from scheduling to dashboards in its own cloud computer, and asks before it sends, pays, signs or deletes. Here is what it does, what it costs, its limits and how it compares.

Anthropic published how the Claude Code team reviews code when Claude writes about 90% of it. Merged PRs more than doubled from June to September while reverts fell by more than 40%. Here is the process and how to copy it.