Computer Use Sandboxes for Apple Device. Use.Computer.

Ultra long horizon benchmarking. Abundant. Website | GitHub

Knowledge work agents should be coding agents. GitHub | Blog

Taxonomies for why models cheat. Abundant. GitHub | Blog

Helping contributors getting tasks to the highest quality. GitHub | [coming soon]

An universal standard for Benchmarking Models. ServiceNow. GitHub | Paper

Trajectory Recording and Capture of Environments. GitHub

Knowledge Graph of all Wikipedia. Stanford and Wikimedia. GitHub | [coming soon]

RL scaling on mathematical reasoning. GitHub

Extracting high quality knowledge graphs from arbitrary text. Stanford. GitHub | Paper