Sandboxing AI agents at the kernel level(greptile.com)

75 points by dakshgupta 1 year ago | 21 comments

Xanadu was waiting for agents(zed.dev)

141 points by nsm 1 month ago | 57 comments

Launch HN: Vespper (YC F24) – SOTA Docx MCP(vespper.com)

32 points by topaztee 28 days ago | 8 comments

Vespper blog post launching its DOCX MCP, a fine-tuned model that lets AI agents edit Word documents via an HTML projection, claiming 3× speed and 2× lower cost.

RTK reports token savings, but our cost benchmarks disagree(quesma.com)

161 points by michalwarda 1 month ago | 80 comments

Benchmarking retrieval for agents on messy real-world company knowledge(kapa.ai)

22 points by emil_sorensen 24 days ago | 2 comments

Kapa blog post introducing Company Knowledge Bench, a benchmark for evaluating agent retrieval over messy real-world company knowledge.

AI agent benchmarks are broken(ddkang.substack.com)

167 points by neehao 1 year ago | 79 comments