from Hacker News

Better LLM response format – A simple trick reduces costs and response time

by livshitz on 7/25/23, 10:10 AM with 6 comments

• by livshitz on 7/25/23, 10:10 AM

  I've composed a post that could be of interest to those of you working with GPT (or any other LLM) and seeking JSON as an output. Here's a simple trick that can help reduce expenses and improve response times.

• by keskival on 7/25/23, 1:07 PM

  I wonder how well LLMs understand YAML Schema format.

  I have found providing JSON Schema to them to be an excellent way to reduce their improvisation in their outputs intended for machine consumption.

• by villgax on 7/25/23, 12:13 PM

  Might make more sense for invoking 3rd party API but for self run LLMs TypeChat w/ JSON is just fine instead of adapting to YAML across your stack