Open SourceHacker News · Sep 22, 2026
Show HN: JevBench, a reproducible benchmark for typed decision models
Hi HN! I built JevBench because Jev kicks ass, and the world deserves to know how the serious open source and fake lookalike projects really perform in comparison. Jev-class models return bounded choices and probabilities instead of text, and are disruptively faster and cheape...
Filed underevalsopen-source
Related stories
Open Source · The Decoder · Nov 20, 2026
Companies will soon be able to run the open-source Hermes Agent from Nous Research directly inside Microsoft Teams. The article Hermes Agent's Collective Wisdom feature turns one employee's AI trick into the whole team's skill appeared first on The Decoder .
Open Source · SiliconANGLE AI · Nov 20, 2026
Agentic AI is reviving an argument over renting versus owning compute, and the model plane — the layer that decides where AI models run — sits at the center of it. Open-source efforts such as Upbound Inc.’s Modelplane route inference across clouds, but many enterprises want th...
Open Source · Hacker News · Nov 20, 2026
Hi HN! Utpal here, I'm one of the founders of OpenComputer. OpenComputer is an open source cloud coding agent for teams that can run in your own cloud account (AWS, GCP, Azure). We run the agent harness and the sandbox on the same durable VM (architecture in the docs [1]). Fir...
Community · GitHub Changelog · Nov 17, 2026
Today, we’re expanding GitHub Copilot Fusion with new models, available on more Copilot surfaces, and results on two public Terminal-Bench leaderboards, giving you more ways to use Fusion and compare… The post GitHub Copilot Fusion updates: more availability, benchmarks, and m...