MIT researchers make language models scalable self-learners

https://news.mit.edu/2023/language-models-scalable-self-learners-0608

It's interesting that they were able to get a model with 350M parameters to outperform others with 175B parameters

6 points · 3 comments · view on lemmy.world

3 Comments

levmyskin@feddit.it · 2 pts · 3y

interesting indeed, even though it seems to work only on specific tasks. I definitely support this direction though. LLMs are getting out of hand (have actually been for a while now), slipped from researchers' grasp into big tech companies'. I think the work that the open source and research community is doing already with the chatgpt lookalike models is incredible

Karo@lemmy.fmhy.ml · 2 pts · 3y

Might finally be able to run one locally on my phone...

Bluetreefrog@lemmy.world · 1 pts · 3y

Aaaand, logic models come back around. Better dust off that old Prolog textbook.