June 2024

##OpenAI makes CriticGPT to find mistakes in GPT-4

OpenAI announced it has trained a model off of GPT-4, dubbed CriticGPT, which aims to find errors in ChatGPT’s code output so they can make improvements and better help so-called human “AI trainers” rate the quality and accuracy of ChatGPT responses.

We’ve trained a model, CriticGPT, to catch bugs in GPT-4’s code. We’re starting to integrate such models into our RLHF alignment pipeline to help humans supervise AI on difficult tasks: https://t.co/5oQYfrpVBu

— OpenAI (@OpenAI) June 27, 2024