build1 publisher
A pinned provider or a LoRA alpha can decide whether a lab's alignment result replicates
A LessWrong post argues that frontier labs publish alignment results with no code and thin methodology. Nobody outside the lab can tell which choices moved the number. It wants a dedicated effort to reproduce them.
Publishers:lesswrong.com
Reality
- Evidence33
- Adoption
- Insufficient
- Hype gap+14
- Incentives45
- Confidence46