News for hackers. Stuff that matters.

A comment on Study mode. Parent comment

Re:Study mode by apparent on Wednesday July 30, 2025 @01:36AM (#44731143)
What is an efficient process for doing this? For each output from LLM1, you paste it into LLM2 and say "does this sound right?"?

If it's that simple, is there a third system that can coordinate these two (and let you choose which two/three/n you want to use?

[ Parent | on HN ]
Re:Study mode by niemandhier on Wednesday July 30, 2025 @02:38AM (#44731434)
You can use existing guardrails software to implement this efficiently:

NVIDIA NeMo offers a nice bundle of tools for this, among others an interface to Cleanlabs API to check for thruthfullness in RAG apps.

[ Parent | on HN ]
Re:Study mode by Paradigma11 on Wednesday July 30, 2025 @01:59AM (#44731234)
Markdown files are everything. I use LLMs to create .md files to create and refine other .md files and then somewhere down the road I let another LLM write the code. It can also do fancy mermaid diagrams.

Have it create a .md and then run another one to check that .md for hallucinations.

[ Parent | on HN ]