cartel criminalmente poco seguido considerando la cantidad de calidad y/o gustos que invitan a la reflexión que publica
mike64_t
mike64_t18 oct, 12:33
I think the observation that LLMs are "bad tutors" in that they cannot precisely probe understanding is accurate. The fact that "upweighting the entire rollout" is stupid is also true. However its not obvious to me that the remedy for that is LLM-reflection as to "what went well". I think this runs into very similar issues of collapse-risk or misallocation of supervision. Because while we might be sucking supervision through a straw, the only thing thats even worse is sucking tainted supervision through a straw.
no es que Mike sea un cartelero de nicho ni nada, pero solo estoy pensando en cuántas cuentas de mierda tienen de 2 a 10 veces más.
30,79K