Contrastive-LM releases CLM-8B, an open model that scores agent actions

A hobby project runs an AI agent called Jev through Pokémon Red, streaming every decision and its odds in a live feed. The creator says Jev decides fast but not fast enough to play Doom, and credits a guide for knowing where to go next.

Documents obtained by the EFF via FOIA show the WISeR pilot, launched in January, was rushed and error-ridden, with one vendor warning CMS a working product by launch was unrealistic. It runs in New Jersey, Ohio, Oklahoma, Texas, Arizona and Washington through 2031.

A C++ CUDA test harness hands kernels to LangGraph-based AI agents that run them, collect benchmarks, and profile via Nsight. Built by bertaye as a side project to learn LangGraph.

A LocalLLaMA poster worked through the rent-vs-buy decision for an 8-GPU HGX H200 server, saying the break-even point landed somewhere they did not expect. The post shares the full calculation and invites corrections.

Google's Product Security team disclosed PageBreak, an internal Gemini-based agent that has uncovered more than 500 XSS vulnerabilities in Google's first-party web apps. It only reports a bug after confirming it with a working exploit against a live environment, giving it a near-zero false-positive rate.

When Claude Code hits a plan's five-hour usage limit mid-response, it now keeps working briefly to reach a graceful stopping point instead of cutting off mid-edit. The extra time comes from a small, fixed allowance drawn from the user's weekly limit.