News for hackers. Stuff that matters.
Re:GLM-5.2 is the new leading open weights model on Artifici... by cromka on Wednesday June 17, 2026 @10:53AM (#48571381)
> it's significant onboarding friction.

It's crazy that apparently writing software without knowing how to edit a single config file is normal now.

Re:GLM-5.2 is the new leading open weights model on Artifici... by johnnyApplePRNG on Wednesday June 17, 2026 @11:30AM (#48571883)
It's crazy that apparently doing math without knowing how to do long division by hand is normal now.
Re:GLM-5.2 is the new leading open weights model on Artifici... by phainopepla2 on Wednesday June 17, 2026 @12:37PM (#48572918)
Absolutely ludicrous comparison
Re:GLM-5.2 is the new leading open weights model on Artifici... by johnnyApplePRNG on Wednesday June 17, 2026 @04:21PM (#48576284)
Is it, though?

I'd argue math is significantly more complex than language.

Re:GLM-5.2 is the new leading open weights model on Artifici... by bityard on Wednesday June 17, 2026 @11:36AM (#48571950)
The real question is: should the file be edited in emacs or vim?
Re:GLM-5.2 is the new leading open weights model on Artifici... by egeozcan on Wednesday June 17, 2026 @01:41PM (#48573875)
For me it's about tolerance. When I was 13, I could and would customize everything, so much that the computer repair shop told my father that their son "likely is a hacker or something".

At 40, I could easily configure claude code to use another model, even if there weren't any official guides with a bit of MITM fun, but I don't want to invest my attention / heavily use something that will most likely break in the near future.

Re:GLM-5.2 is the new leading open weights model on Artifici... by scotty79 on Thursday June 18, 2026 @04:19AM (#48582392)
You can ask the agent to change its own configs. Pi does that by default.