Max Bartolo (@max_nlp) 's Twitter Profile
Max Bartolo

@max_nlp

I lead the Command modelling team at @Cohere and co-chair the @DynabenchAI @MLCommons working group. Prev @DeepMind, @MetaAI / FAIR & @BloomsburyAI.

ID: 794224315315224576

linkhttp://maxbartolo.com calendar_today03-11-2016 17:06:47

781 Tweet

2,2K Followers

759 Following

Max Bartolo (@max_nlp) 's Twitter Profile Photo
Max Bartolo
@max_nlp

5 months ago

Can LLMs be incentivised to generate token sequences (in this case preambles) that condition downstream models to improve performance when judged by reward models? Yes! ✅