Mazin K
9 followers · 9 following · 293 views
on the atlas — 8
- Inside the Transformer: The Life of a Token - Aleksa Gordić2 savers
- Neel Nanda MATS 9.0 Stream - Admissions Procedure + FAQ1 savers
- Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples1 savers
- 2312.069423 savers
- AI Control: Improving Safety Despite Intentional Subversion — LessWrong5 savers
- The case for ensuring that powerful AIs are controlled2 savers
- AI catastrophes and rogue deployments - by Buck Shlegeris2 savers
- Introduction - SITUATIONAL AWARENESS: The Decade Ahead50 savers