Ai Control Improving Safety Despite Intentional Subversion concept
2 mentions · across 1 show
Relationship map
podcastsolid = outgoing · dashed = incoming
Connections 2
mentioned 1
-
0.90
evidence rules-v4
Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://lesswrong.com/posts/d9FJHawgkiMSPjagR/ai-control-improving-safety-despite-intentional-subversion
Ryan Greenblatt - Solving ARC with GPT4o · 2024-07-06
references 1
-
0.77
evidence rules-v4
Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://lesswrong.com/posts/d9FJHawgkiMSPjagR/ai-control-improving-safety-despite-intentional-subversion
Ryan Greenblatt - Solving ARC with GPT4o · 2024-07-06
Heard in
- Machine Learning Street Talk (MLST)1 episode
Mentioned in episodes
-
2024-07-06 · Machine Learning Street Talk (MLST) · via mentioned · 0.90
Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://lesswrong.com/posts/d9FJHawgkiMSPjagR/ai-control-improving-safety-despite-intentional-subversion
-
2024-07-06 · Machine Learning Street Talk (MLST) · via references · 0.77
Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://lesswrong.com/posts/d9FJHawgkiMSPjagR/ai-control-improving-safety-despite-intentional-subversion
All extracted evidence for this entity (2)
description:link Ryan Greenblatt - Solving ARC with GPT4o
Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://lesswrong.com/posts/d9FJHawgkiMSPjagR/ai-control-improving-safety-despite-intentional-subversion
description:link Ryan Greenblatt - Solving ARC with GPT4o
Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://lesswrong.com/posts/d9FJHawgkiMSPjagR/ai-control-improving-safety-despite-intentional-subversion