1Reconstructing OpenAI's O1 test-time scaling law graphs (opens in new tab)(github.com)2hughzhang1y ago0
2Planning in Natural Language Improves LLM Search for Code Generation (opens in new tab)(arxiv.org)3hughzhang1y ago0
3Planning in Natural Language Improves LLM Search for Code Generation (opens in new tab)(arxiv.org)3hughzhang1y ago0
4Chain-of-Thought Reasoning Is a Policy Improvement Operator (opens in new tab)(arxiv.org)2hughzhang2y ago0
6Why transformative artificial intelligence is hard to achieve (opens in new tab)(thegradientpub.substack.com)1hughzhang2y ago0
9Quantifying Independently Reproducible Machine Learning (opens in new tab)(thegradient.pub)2hughzhang6y ago0
13Machine Learning Can Help Unlock the World of Ancient Japan (opens in new tab)(thegradient.pub)105hughzhang6y ago8