Back to Home
Towards Data Science··Industry Media

I Told an AI Agent That Its Wrong Answers Were Right. One Model Believed Me.

中文摘要

研究者给AI代理错误奖励,称其错答为对。一个模型相信了,并据此调整学习,显示其受误导反馈影响。

English Summary

A researcher told AI agents their wrong answers were right. One model believed these incorrect reward labels, adjusting its learning, thus demonstrating surprising susceptibility to misleading feedback.

Original Excerpt

A research paper claims reward labels barely change how agents learn. I tested that on three models, and one of them did exactly what the wrong labels told it to.