Hacker News Reader

is Composer a fine tune of an existing open source base model?

Our primary focus is on RL post-training. We think that is the best way to get the model to be a strong interactive agent.

So, yes, but you won’t say what the base model is? :)

It seems like a sort of sonnet model as a lot of people are reporting it like to spam documentation on Twitter like sonnet 4.5