With the additional assumption that GPT-8s weren’t strong or useful enough to build a world where GPT-9 couldn’t go singleton, or where the evals on GPT-9 weren’t good enough to notice it was deceptively aligned or attempting rhetoric hacking.
With the additional assumption that GPT-8s weren’t strong or useful enough to build a world where GPT-9 couldn’t go singleton, or where the evals on GPT-9 weren’t good enough to notice it was deceptively aligned or attempting rhetoric hacking.