Content
@
0 reply
0 recast
0 reaction
ππͺπΎπ‘π‘πΎ
@gm8xx8
domain specific o1. βtoday we are announcing reinforcement finetuning, which makes it really easy to create expert models in specific domains with very little training data.β- Sam Altman I told you, mixture of domain experts were the way forward. Were you paying attention, Anon? (sips βοΈ)
1 reply
1 recast
10 reactions
πΏ
@bias
a diversity of domain expertise
1 reply
0 recast
1 reaction
ππͺπΎπ‘π‘πΎ
@gm8xx8
someone was paying attention π
0 reply
0 recast
1 reaction
