ProofOfThought: LLM-based reasoning using Z3 theorem proving

Re:ProofOfThought: LLM-based reasoning using Z3 theorem proving by striking on Saturday October 04, 2025 @03:55PM (#45476204)

Not sure if I've been using it wrong but I've tried using the Zod-to-structured-output helper with GPT-5 and often gotten weird stuff like trailing commas that break a parse or seeing multiple JSON responses in the same response.

Ultimately there are still going to be bugs. For this reason and several others you'll still need it wrapped in a retry.

[ Parent | on HN ]

Re:ProofOfThought: LLM-based reasoning using Z3 theorem proving by sigmoid10 on Saturday October 04, 2025 @04:01PM (#45476238)

Yeah that sounds 100% like a user or middleware issue. Don't bother with these wrappers, they are always outdated anyways. Learn how to use the API directly, it will save you a ton of headaches. And it's really not that hard.

[ Parent | on HN ]

Re:ProofOfThought: LLM-based reasoning using Z3 theorem proving by striking on Saturday October 04, 2025 @04:11PM (#45476303)

No, we're using the OpenAI vendored version of zod-to-json-schema via https://github.com/transitive-bullshit/openai-zod-to-json-sc..., and applying it directly to the `json_schema` field of the OpenAI API. Maybe we have a subtle bug somewhere but I'd expect a 400 response if we were genuinely sending a malformed request.

[ Parent | on HN ]