Aspiring AI/ML Engineer | Kaggler | Open Source Contributor | Hacksquad 2023 Winner | Reflex Hacktoberfest AI Champion | Quine's AI Themed Quest 1st Runner-Up (x2)
We are entering in the era of self improvement in Technology. Let's see what will be the results. Though there is hallucination problem with CriticGPT as listed, but it can be fixed later on, as it out performance individual Human and combination of Human and CriticGPT, alone.
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://lnkd.in/gbAue2fZ