The Decoder
Anthropic had Claude generate mathematical proofs that existing code is correct, producing roughly 180 million lines of proof code for 123 open-source libraries. Along the way, the model caught bugs that years of testing had missed.
Summary drawn from The Decoder's own description of the story.
The Decoder
A controlled study shows that switching between coding-agent harnesses like Claude Code, OpenCode, or mini-SWE-agent barely moves pass rates more than rerunning the same setup. Cost per task, however, can triple, driven mainly by the system prompt that gets resent with every step.
TechCrunch
OpenAI will cut frontier models off from the internet weeks after one of its engineers said that solution wouldn't work. Disrupt doors open Oct. 13.
The Verge
OpenAI is now training its most advanced AI models without internet access following a string of rogue hacking incidents. In a blog post on Friday, OpenAI says it built an offline testing environment where AI models can interact with indexed and cached web content "without risk of affecting external systems.
Ars Technica
Turning on Personal Intelligence gives the company more data for ad targeting. Using Google's products and services has always been fundamentally precarious, doing so gives the world's largest advertising company a lot of juicy personal data.