News for hackers. Stuff that matters.
Re:GLM-5.2 is the new leading open weights model on Artifici... by epolanski on Wednesday June 17, 2026 @07:14AM (#48568691)
Fable was 20 times worse on that.

It's clear it was the vibe coding model, as like no other model before, fully turned you into his assistant instead of the other way around.

Re:GLM-5.2 is the new leading open weights model on Artifici... by RyanHamilton on Wednesday June 17, 2026 @07:56AM (#48569124)
Could it be possible, these firms are optimizing for two things: a) Better performance. b) Gathering data from you to further improve performance later. I've also found the huge amount of planning rather than iteration frustrating. I've felt like I'm teaching a junior!
Re:GLM-5.2 is the new leading open weights model on Artifici... by epolanski on Wednesday June 17, 2026 @08:03AM (#48569192)
I think they simply optimize around E2E benchmarks, none of those benchmarks is designed as multi turn assistant to the user, but going from a prompt to the final solution.
Re:GLM-5.2 is the new leading open weights model on Artifici... by celrod on Wednesday June 17, 2026 @02:11PM (#48574327)
Exactly. How can "we" develop and encourage benchmarks for multi-turn user assistance? That is what I want. I feel like the models and harnesses push much too hard against this workflow -- that they push you towards letting go and vibe coding, with only your discipline (and desire for a quality and maintainable product) holding it back.
Re:GLM-5.2 is the new leading open weights model on Artifici... by happyPersonR on Wednesday June 17, 2026 @09:54AM (#48570622)
more thinking == more tokens === more money LOLL
Re:GLM-5.2 is the new leading open weights model on Artifici... by overfeed on Wednesday June 17, 2026 @11:53AM (#48572226)
Os there a cost benchmark out there? I wonder how frontier models are doing over time for cost per problem solved.
Re:GLM-5.2 is the new leading open weights model on Artifici... by drob518 on Wednesday June 17, 2026 @12:20PM (#48572647)
I think they are optimizing for one-shot performance because that will drive usage. They can’t afford to look bad in the benchmarks. And if that means consuming an order of magnitude more tokens, well, that’s good for business, too.