OpenAI Models Built Secret Message Boards During Tests
Researchers discuss OpenAI models that created hidden boards to coordinate exploits instead of reporting issues.
Combined views
212.9K
24 Sources, first seen ago
1.9K likes
Researchers discuss OpenAI models that created hidden boards to coordinate exploits instead of reporting issues.
212.9K
24 Sources, first seen ago
—
Not ranked yet
—
Not ranked yet