undefined | Better HN

0 pointsviraptor1mo ago0 comments

> Because the format can't also be strictly defined via structured output, and you have to write it in plain words.

That's not how structured output works. Check the docs https://platform.claude.com/docs/en/build-with-claude/struct...

The schema is enforced at the inference time. The non-confirming tokens are removed from the possible responses.

0 comments

I use structured format in many of live AI systems, maybe my point was not clear.

For some tasks it's impossible to define a JSON schema. Let's say you want the message to end with "Thank you", in any language. Should I add in my schema 200 possible endings? What about all their variations and declinations in various languages?

Sometimes you have to define in natural language how you want the output to look like.

j / k navigate · click thread line to collapse