Essay · AI Blog · Lil'Log · Lilian Weng
Why We Think
Summary · 摘要
Special thanks to John Schulman for a lot of super valuable feedback and direct edits on this post. …
阅读原文 lilianweng.github.io
继续读 · Essay · AI Blog
Harness Engineering for Self-ImprovementLil'Log · Lilian Weng · 138 天前Scaling Laws, CarefullyLil'Log · Lilian Weng · 148 天前Reward Hacking in Reinforcement LearningLil'Log · Lilian Weng · 721 天前Extrinsic Hallucinations in LLMsLil'Log · Lilian Weng · 865 天前Diffusion Models for Video GenerationLil'Log · Lilian Weng · 951 天前