← Back to context Comment by tekne 2 days ago The raw pretrained models make the errors, I believe -- we then reinforcement-learn them out. 1 comment tekne Reply Tomte 2 days ago That‘s interesting! Do you have a paper or blog post or so at hand that shows examples of raw and RL‘ed output?
Tomte 2 days ago That‘s interesting! Do you have a paper or blog post or so at hand that shows examples of raw and RL‘ed output?
That‘s interesting! Do you have a paper or blog post or so at hand that shows examples of raw and RL‘ed output?