Open SourceHacker News (MCP) · Oct 13, 2026
Show HN: Parsimony – an open-source benchmark for how much code AI models add
Existing benchmarks measure solve rate and token output/cost, but don't punish excess code, which makes a codebase harder to work with in the long term. I wanted to measure this since it matters most for long-term projects. Method: it takes the patches that benchmarks already ...
Filed underanthropicopenaievalsopen-source
Related stories
Community · OpenAI Blog · Oct 28, 2026
See how Legora uses OpenAI models, ChatGPT, and Codex to accelerate legal workflows, expand contract analysis, and free lawyers to focus on higher-value work.
Community · TechCrunch AI · Oct 22, 2026
Claude Duet is available through waitlist for Pro and Max plan users.
Community · OpenAI Blog · Oct 21, 2026
See how OpenAI, PerturbAI, and Scripps Research used distributed AI agents to uncover promising research leads in data from millions of brain cells.
Open Source · OpenAI Blog · Oct 21, 2026
Patch the Planet connects security researchers, maintainers, and incident responders to help address critical vulnerabilities across open source.