LessWrong AI
· Communities
Fixing rewards for NLA to reduce confabulation
Hello,This is my first post on Lesswrong. Hope my contribution makes the world a better and safer place.Note: 1. This post is 100% human-written. 2. Full paper in preparation for ICLR 2027Anthropic's NLA(Natural Language Autoencoder) is mostly confabulated... until I fixed the reward.The NLA(The Natural Language Autoen