1
How confessions can keep language models honest
OpenAI秘密武器：让大模型学会“认错”，诚实度飙升的秘密在这篇研究里！
OpenAI researchers are testing “confessions,” a method that trains models to admit when they make mistakes or act undesirably, helping improve AI hone…
OpenAI秘密武器：让大模型学会“认错”，诚实度飙升的秘密在这篇研究里！
OpenAI researchers are testing “confessions,” a method that trains models to admit when they make mistakes or act undesirably, helping improve AI hone…