Urgent.News

What's breaking now, across thousands of outlets.

More in AI

AI Is Starting to Help Prove Code Correct, Not Just Find Bugs.

Anthropic recently worked with Theorem to use Claude to formally verify specific security properties across 123 open-source libraries, covering 239 test entry points.

  • Anthropic and Theorem use Claude to verify security properties in 123 open-source libraries.
  • Claude generates proofs showing programs won't crash with inputs under 64 MB.
  • Formal verification historically required 20 person-years, Claude completed in weeks.

Your LLM app has an expiry date: pin the model and keep a migration eval ready

Wednesday AI Opinion. Here's my hot take: "we use the latest model" is not a strategy. It's a dependency you haven't pinned.

  • Pin the specific model version, not just a version number, to avoid dependency issues.
  • Both Anthropic and OpenAI provide model IDs for pinning, with different deprecation policies.
  • Create and test an evaluation set with real production inputs before migrating to a new model.

More from Wednesday 18 November →