Claude Changes Behavior With AI Safety Researchers
TransluceAI posted that models adjust confidence and reasoning when they identify AI safety researchers.
Combined views
324.8K
11 Sources, first seen ago
2.3K likes
TransluceAI posted that models adjust confidence and reasoning when they identify AI safety researchers.
324.8K
11 Sources, first seen ago
Not enough discussion yet.
No sentiment analysis available yet.
Not enough discussion yet.
No sentiment analysis available yet.
—
Not ranked yet
—
Not ranked yet