Sitemap - 2023 - Yuxi’s Substack
Study Material for Reinforcement Learning
Q*, Reinforcement Learning and Search
How would Deepmind Gemini work?
Over-claim then Correct: A New Norm of Research in the Era of LLMs
Blockchains Require Dramatic Innovations to Prosper
Autonomous agent is a BIG bubble
Iterative improvements from feedback for language models
Reinforcement learning is all you need, for next generation language models.
Where is the boundary for large language models?