Goblin
News
AI news, distilled.
|
News
About
News
About
Filtered by:
Alignment Research
Clear
Titles
Summaries
8
OpenAI Publishes Misalignment Framework and Discloses 6 Concerning Model Behavior Incidents
Updated Sep 17
Safety
14
2d ago
8
OpenAI Publishes Misalignment Framework and Discloses 6 Concerning Model Behavior Incidents
Top
Upd Sep 17
Safety
· 14 srcs · 2d ago
Discuss
7
AI Safety Researcher Paul Christiano Joins OpenAI Board With Dire Alignment Warning
Updated Sep 10
Safety
6
Sep 10
7
AI Safety Researcher Paul Christiano Joins OpenAI Board With Dire Alignment Warning
Top
Upd Sep 10
Safety
· 6 srcs · Sep 10
Discuss
Filters
Signal
Title
Category
Sources
Posted
Discuss
