Remix.run Logo
sosodev 3 days ago

A month seems plenty long enough. They're not rebuilding the entire model from scratch. It's just getting Fable to act as a teacher model for some of the final reinforcement learning on the base that Kimi already had.

epolanski 3 days ago | parent [-]

I think that would also be a bad idea, as all models opus 4.6 got increasingly smarter, but also crappier at following instructions or genuinely assisting.

They just try to figure out what the goal is and hyper focus on solving it.

Heh, even just telling fable don't commit doesn't work half the times, let alone more complex instructions.