A self-hosted TypeScript middleware that lets Claude Code, Codex and other CLI agents run autonomously in the background and ping you only for key decisions.
A new supervision recipe forces models to actually use retrieved evidence, not just paste it next to a prediction, with large gains in radiology verification.
A new personality benchmark finds frontier closed models write with more truthfulness and structure, while open weights lean into filler and bottom-line summaries.
A new arXiv paper tackles cell lineage reconstruction when only a fraction of cells are labeled, combining 2.5D and 3D detectors with joint lineage optimization.
Prime Intellect audited popular LLM benchmarks and found broken graders, ambiguous tasks, and web-based cheating that significantly change reported model rankings.