Notes on the Alignment Forum's Value Learning sequence curated by Rohin Shah. ambitious value learning : the idea of learning 'the human…
The problem of [ exposure bias ] (where an autoregressive sequence model goes off the rails of its training distribution) comes up as a…
Considering training an [ autoregressive ] model of sequence data (text, audio, action sequences in [ reinforcement learning ], etc.), which…
In any human-to-human interaction, language carries some very important high-order bits, but it can only carry a few bits. It can help…