build1 publisher
Llama-3.1-8B's first turn predicts the harmful answer nine points above the baseline floor
Across 192 identically worded persuasion chains against Llama-3.1-8B-Instruct, the model gave in 109 times, and a direction read at turn one predicted which runs would break at 0.706 against a 0.617 floor.
Publishers:lesswrong.com
Reality
- Evidence42
- Adoption
- Insufficient
- Hype gap+15
- Incentives40
- Confidence48