Hacker News new | ask | show | jobs
by wanderingmind 670 days ago
Kind of a noob question, is it possible to design a GAN type network with LLM, where one (or many) LLMs generate outputs, while a few other LLMs validate or discriminate them and thus improving generator LLMs accuracy.
1 comments

Yes, you can use AI to spot errors in AI output. Done before with good results, but it requires to run 2 different, but equally good, AI models in parallel, which is way more expensive than 1 model.
"which is way more expensive than 1 model."

In this case "way more" means exactly 2x the cost.