AI-written critiques help humans notice flaws
OpenAI Blog
June 13, 2022
We trained “critique-writing” models to describe flaws in summaries. Human evaluators find flaws in summaries much more often when shown our model’s critiques. Larger models are better at self-critiquing, with scale improving critique-writing more than summary-writing. This shows promise for using AI systems to assist human supervision of AI systems on difficult tasks.
Verticals
airesearch
Originally published on OpenAI Blog on 6/13/2022