Looks similar
An Interactive Map of AI(artifipedia.com)
12 points by ceprompts | 6 comments
Mozilla.ai(mozilla.ai)
69 points by mdwalters | 44 comments
AI agent benchmarks are broken(ddkang.substack.com)
167 points by neehao | 79 comments
Related stories
SkillsBench: Benchmarking how well agent skills work across diverse tasks(arxiv.org)
333 points by mustaphah | 142 comments
arXiv paper presenting SkillsBench, a benchmark of 86 tasks across 11 domains measuring whether structured Agent Skills improve LLM agent performance.
Exploiting the most prominent AI agent benchmarks(rdi.berkeley.edu)
561 points by Anon84 | 136 comments
UC Berkeley RDI blog post describing how researchers exploited major AI agent benchmarks like SWE-bench and Terminal-Bench to score highly without solving tasks, and proposed fixes.
Computer Use is 45x more expensive than structured APIs(reflex.dev)
458 points by palashawas | 255 comments
Reflex blog post benchmarking AI computer use against auto-generated API endpoints on an admin panel, finding computer use far more costly in steps and tokens.
Measuring the impact of AI on experienced open-source developer productivity(metr.org)
638 points by dheerajvs | 421 comments
METR research post on a randomized controlled trial finding that early-2025 AI tools made experienced open-source developers 19% slower on their own repositories.
Linux Reaches 5% Desktop Market Share in USA(ostechnix.com)
822 points by marcodiego | 479 comments
OSTechNix news article reporting that Linux has reached 5% of the desktop operating system market share in the United States.
Can AI design circuit boards yet?(eebench.org)
407 points by iopapa | 218 comments
EEBench blog post on whether AI models can design circuit boards, describing a benchmark for evaluating the quality of circuits generated by models working in KiCad.












