Back to News Hub
🤖OpenAI
June 13, 2022
Funding & Investment

AI-written critiques help humans notice flaws

Overview

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.

Read the full story at OpenAI

This publisher only syndicates a short excerpt by RSS. The full article — with all the detail, quotes, and context — lives on their site.

Open original article

Continue Learning

Originally published by OpenAI
Read the original

Comments

Sign in to join the conversation