SFT Is Bad RL
justinchiu.netlify.app·4d·
Discuss: Hacker News
Pro AI – Human Segregation
onlyluck.substack.com·5h·
Discuss: Substack
Google DeepMind Formal Conjectures
google-deepmind.github.io·21h·
Discuss: Hacker News
Market of Words
fakepixels.substack.com·1d·
Discuss: Substack