The Societal Impact of Cognitive Offloading
See more →
Archive
Collected posts, papers, and highlights in one place.
TDFlow: Agentic Workflows for Test Driven Development
See more →
Working on PaperBench with OpenAI
See more →
Scaling Natural-Language Graph-Based Test Time Compute for Automated Theorem Proving
See more →
Semantic Self-Consistency: Enhancing Language Model Reasoning via Semantic Weighting
See more →