alt Hacker NewsThat is not at all what Tao said.
https://mathstodon.xyz/@tao/113132502735585408
"Here the results were better than previous models, but still slightly disappointing: the new model could work its way to a correct (and well-written) solution if provided a lot of hints and prodding, but did not generate the key conceptual ideas on its own, and did make some non-trivial mistakes. The experience seemed roughly on par with trying to advise a mediocre, but not completely incompetent, (static simulation of a) graduate student. "
Yea it does seem pretty clear that it's mainly Terrance's contributions to the context window that is bringing the model to the right answer