News for hackers. Stuff that matters.
Re:Structured Output from LLMs (Without Reprompting!) by roseway4 on Sunday July 16, 2023 @10:31PM (#36753423)
When you say “our model”, are you using a custom LLM for completions vs OpenAI or other LLM vendor?
Re:Structured Output from LLMs (Without Reprompting!) by sandkoan on Sunday July 16, 2023 @10:54PM (#36753547)
Custom LLM—hence the self-hostability.