Google researchers find a way to keep self-improving AI agents from memorizing their tests
Google researchers find a way to keep self-improving AI agents from memorizing their tests
自我提升的AI代理往往会记住其测试任务，因此在新的任务中其提升效果会减少或消失。谷歌研究人员提出了一种新方法RRSI，可以遏制这种效应，并在使用比未经正则化的版本少约30%的标记的情况下，将未见过的基准测试得分提高多达4.7分。文章《谷歌研究人员找到一种方法，防止自我提升的AI代理记住其测试》首先出现在The Decoder上。
Self-improving AI agents tend to memorize their test tasks, so their gains shrink or disappear on new ones. RRSI, a new method from Google researchers, reins in this effect and lifts scores on unseen benchmarks by up to 4.7 points while using about 30 percent fewer tokens than an unregularized version. The article Google researchers find a way to keep self-improving AI agents from memorizing their tests appeared first on The Decoder .
应来源方要求，这里只提供摘要与原文入口。完整内容请阅读原文。
来源：The Decoder · the-decoder.com