OpenAI has introduced CriticGPT, a new AI model that can help identify mistakes in code generated by ChatGPT. The tool will improve the process of alignment in AI systems and will eventually make the outputs from large language models more accurate.
Built using their flagship AI model GPT-4, CriticGPT was built to help human AI reviewers at checking code generated by ChatGPT. This is unlike the other models from the company, which are consumer-facing.
According to OpenAI, code reviewed by CriticGPT can outperform unreviewed code by 60 per cent. The company is currently integrating CriticGPT-like models into the RLHF labelling pipeline to assist AI trainers in evaluating outputs from advanced AI systems.
OpenAI says models like CriticGPT can help make ChatGPT more accurate with subtle mistakes and can also spot errors that humans might miss, as models become more knowledgeable. The process of training CriticGPT included editing ChatGPT-generated code manually and introducing new errors into the code along with sample feedback to train the model to easily identify common and not-so-common mistakes.
Like human suggestions, CriticGPT’s suggestions are not always correct. However, OpenAI says that the combination of the Human+CriticGPT team is said to outperform unassisted human trainers.
See What’s Next in Tech With the Fast Forward Newsletter
Tweets From @varindiamag
Nothing to see here - yet
When they Tweet, their Tweets will show up here.
