[jimmyed]

> This model completes tasks like code generation more thoroughly than the previous preview model and is intended to reduce cases of “laziness” where the model doesn’t complete a task.

How does one solve for this? Wrangling the prompt with "please don't be lazy", or are there inference tricks like running thru the weights differently/multiple times?

[minimaxir]

RLHF harder.

[Karuma]

Maybe removing the lazy posts from the training data.

[dang]

Please don't make the thread worse by crossing into off-topic attacks like this.

If you see a post or an account that ought to have been moderated but hasn't been, the likeliest explanation is that we didn't see it. If you want to help, emailing us at [e-mail] is best.

[nickthegreek]

fyi, they got banned for another comment on this post.