I think @typesafeai Jev has solved a much bigger AI problem than it first appear

I think @typesafeai Jev has solved a much bigger AI problem than it first appears: LLMs shouldn’t have to think about everything. A huge amount of “reasoning” is actually classif

I think @typesafeai Jev has solved a much bigger AI problem than it first appears: LLMs shouldn’t have to think about everything. A huge amount of “reasoning” is actually classification: Given this context, which of these 100 possibilities is most likely? If fast