Pinned Loading
-
ate-series
ate-series PublicAgent Teams Eval: experimental series comparing Claude Code Agent Teams vs subagents across bug-fixing, feature implementation, and architecture design.
TeX
-
crit-thinking
crit-thinking PublicEmpirical study of latent quality in LLMs under critical engagement
Python
-
synthoracle
synthoracle PublicSynthetic oracle benchmark for evaluating scientific reasoning in optimization agents
Python
-
x-algorithm-enhancements
x-algorithm-enhancements PublicEnhancements to xAI's x-algorithm: JAX optimization, RL reward modeling, multimodal retrieval
Python
-
originality
originality PublicA research program on intellectual plurality: why original thought is hard, and whether it's become harder despite rising demographic diversity.
Python 1
If the problem persists, check the GitHub status page or contact support.


