Nice, agreed. This is basically why I don’t see any hope in trying to align super-LLMs. (this and several similar categories of plausible failures that don’t seem avoidable without dramatically more understanding of the algorithms running on the inside).
Nice, agreed. This is basically why I don’t see any hope in trying to align super-LLMs. (this and several similar categories of plausible failures that don’t seem avoidable without dramatically more understanding of the algorithms running on the inside).