Wrong, custom "specs" i.e. schemas, are literally all we have for "real" guardra... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

Der_Einzige 18 days ago | parent | context | favorite | on: GLM 5.2 vs. Opus

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.

scwoodal 18 days ago [–]

Enforcing structured outputs from LLMs is not the same thing as using linters, formatters, static analysis to control how an agent writes code.

Der_Einzige 18 days ago | [–]

No, it's not. It's strictly better.

scwoodal 18 days ago | | [–]

Can you share examples, links to Github of this approach? I'd like to learn.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact