Existing models, Fable and 5.6 Sol, were also able to prove the existence of nonsofic groups (last night before the paper release)
My thoughts after daily driving Silico:
It makes research substantially more joyful and exciting, allowing me to accomplish more and explore a more diverse set of methods and ideas. It's sticky; I don’t want to go back to not using it. The agents have more freedom and agency than in Claude Science. Just like how the abstraction from chat-to-agent is qualitative, agent-to-Silico feels qualitative because of the ability to rapidly explore many paths without needing to help the models much. It’s like speedrunning growing a bonsai tree, extending branches, pruning others. I tried Silico on both genomics and mechanistic interpretability. Also, tell me what I should try next
Show more
Goodfire's Silico decided to show me this result of how representation of days of the week emerges over pretraining
High praise from Opus 4.8 in Claude Code
This was a joke but Mistral is now the main hope of Europe given the recent Fable ban. This is a great opportunity for Mistral—they'd have a monopoly
Before Fable was locked in federal prison, they made a new type of spline designed to fit extremely high dimensional (e.g. 30D) objects. Currently benchmarking it to see if it's good
Show more
Fable "borrowed" "a trick from quantum field theory" 😐
Fable uses a Chinese word (meaning real/genuine) in Claude Code, and the word makes sense in the sentence. No Chinese in context
