#funsearch — Public Fediverse posts

https://www.technologyreview.com/2023/12/14/1085318/google-deepmind-large-language-model-solve-unsolvable-math-problem-cap-set/5

ICYMI
LLM discovers solution to long-standing scientific puzzle—producing verifiable new info…“It’s not in the training data—it wasn’t even known.”

#FunSearch combines a LLM called Codey, a version of Google’s PaLM 2 that is tuned on #computercode…

research scientist at #DeepMind, Alhussein Fawzi: “To be very honest with you, we have hypotheses, but we don’t know exactly why this works. In the beginning of the project, we didn’t know whether this would work at all.”