Comment by wolttam

6 days ago

I didn't think they'd actually release a model that was worse than the open-weight frontier and at a higher price-point. Wow.

9 comments

wolttam

Reply
LUmBULtERA  6 days ago

That's yet to be determined. I think a lot of open-weight models are benchmaxxed and their usefulness for many tasks are not represented by those.

  • enraged_camel  6 days ago

    Yes, this has been my experience. They all struggle with long-horizon tasks and eventually start going in circles.

winrid  5 days ago

Today I tested GLM 5.2 by giving it an example stylesheet and told it to change the background color of a submit button.

It then hallucinated the submit button class...

s3p  6 days ago

Why did the other reply to this get flagged as dead? It was a comment about how someone would come out saying that Sonnet 5 would be better on the pelican test and therefore it has to be good. But I guess HN loves pelican SVGs so much that you're not allowed to criticize it.

  • steveklabnik  6 days ago

    If you look at the account history, it's pretty clearly an account-level thing, not a comment-level thing.