Content pfp
Content
@
0 reply
0 recast
0 reaction

𝚐π”ͺ𝟾𝚑𝚑𝟾 pfp
𝚐π”ͺ𝟾𝚑𝚑𝟾
@gm8xx8
domain specific o1. β€œtoday we are announcing reinforcement finetuning, which makes it really easy to create expert models in specific domains with very little training data.”- Sam Altman I told you, mixture of domain experts were the way forward. Were you paying attention, Anon? (sips β˜•οΈ)
1 reply
1 recast
10 reactions

πŸ—Ώ pfp
πŸ—Ώ
@bias
a diversity of domain expertise
1 reply
0 recast
1 reaction