The team turned existing fuzz tests from Google's OSS-Fuzz project into formal specifications over compiled RISC-V binaries, then had Claude write the proofs and a Rocq proof checker validate them. The post reports proofs for 239 entry…
In the News: October 22, 2026 (Evening)
Anthropic reports Claude proved no-crash properties on 123 open-source libraries at the machine-code level, and two engineering teams describe how they gate agent work with deterministic checks.
Evening edition
Machine-readable
Download Markdown
Story
Anthropic and Theorem report Claude proving no-crash properties on 123 open-source libraries
Read story →
Story
Snap describes an experiment loop where the harness is deterministic and the agent works only at the edges
Snap's ML engineers run an agent platform called Alchemist, built around a harness that validates plans, submits runs, polls results and enforces budgets as code the agent calls rather than behavior it improvises. The agent proposes…
Story
Imprint's "small-change" lets automated checks approve a narrow class of pull requests
Larson reports that Imprint's average engineer merges 4x more pull requests than two years ago, and that median review time rose from 33 to 77 minutes. A pull request qualifies as a small-change if it is under 1,000 lines, has no P1 or P2…