News for hackers. Stuff that matters.
Re:GLM 5.2 vs. Opus by Der_Einzige on Monday June 22, 2026 @10:23AM (#48630547)
Wrong, custom "specs" i.e. schemas, are literally all we have for "real" guardrails with LLMs.

https://developers.openai.com/api/docs/guides/structured-out...

Nothing else operates on the logprobs level and literally bans continuations that fail your schema.

Re:GLM 5.2 vs. Opus by scwoodal on Monday June 22, 2026 @10:33AM (#48630725)
Enforcing structured outputs from LLMs is not the same thing as using linters, formatters, static analysis to control how an agent writes code.
Re:GLM 5.2 vs. Opus by Der_Einzige on Monday June 22, 2026 @10:36AM (#48630769)
No, it's not. It's strictly better.
Re:GLM 5.2 vs. Opus by scwoodal on Monday June 22, 2026 @10:44AM (#48630895)
Can you share examples, links to Github of this approach? I'd like to learn.