we keep hearing "the bobot is getting better at writing code all the time" and you know what we keep not seeing? a single god damn bit of improvement. it generates verbose
dogshit full of useless indirection, misleading comments, redundant expressions, and outright nonsense. you people think this is good? from here it looks like you have no fucking skill at judging code quality
Conversation
Notices
-
Embed this notice
mx alex tax1a - 2020 (6) (atax1a@infosec.exchange)'s status on Saturday, 25-Jul-2026 04:31:19 JST
mx alex tax1a - 2020 (6)
-
Embed this notice
iced depresso (icedquinn@blob.cat)'s status on Saturday, 25-Jul-2026 04:31:18 JST
iced depresso
@atax1a actually ended up taking out all of the code from GLM and went back to generating it with macros from xml in the one project i ever used a bot on.
its a real crapshoot when the things properly infer "unroll this stream in to an outline based on this stack machine principle" and when they absolutely fuck up "your job is to just check this in a single order." -
Embed this notice
mx alex tax1a - 2020 (6) (atax1a@infosec.exchange)'s status on Saturday, 25-Jul-2026 04:31:19 JST
mx alex tax1a - 2020 (6)
the patterns it turns out are so mind-bendingly wrong that we haven't even encountered them in even the rankest of beginners. people do not write code like that. it's a fucking farce
-
Embed this notice
mx alex tax1a - 2020 (6) (atax1a@infosec.exchange)'s status on Saturday, 25-Jul-2026 04:41:07 JST
mx alex tax1a - 2020 (6)
@icedquinn the bobot is simply a Code Worsener
-
Embed this notice
iced depresso (icedquinn@blob.cat)'s status on Saturday, 25-Jul-2026 04:41:07 JST
iced depresso
@atax1a i think there's a fundamental issue the LLM is basically a cheap intern but its still sidestepping that you shouldn't need interns.
people will deadass use a hyperscaler datacenter and two million tokens instead of just write a little xml file and template expand it to code :blobcatgoogly:
-
Embed this notice