Re:Claude was trained on protein sequences at scale
by jfrbfbreudh on Wednesday November 18, 2026 @09:56AM
(#50547062)
Given that there are quite a few quants who have switched over from HFT to AI research, it’s not surprising that AI models would be trained on unconventional / unexpected data sources. The fact that they included this training in their general release model shows that their internal experiments demonstrated that it was better including it than not.
But Anthropic has already started operating their wet lab, so it’s also entirely possible that Fable 5.2 is a distilled version of an internal model (though I doubt they would actually be that reckless).
But Anthropic has already started operating their wet lab, so it’s also entirely possible that Fable 5.2 is a distilled version of an internal model (though I doubt they would actually be that reckless).