build1 publisher
Competing finetuning overrode a midtraining run 3,800 times its size
A LessWrong stress test reports that roughly 50K tokens of opposing finetuning beat 190M tokens of midtrained motivations, in an implementation its authors assembled from the best public description of the method.
Publishers:lesswrong.com
Reality
- Evidence38
- Adoption22
- Hype gap+20
- Incentives55
- Confidence45