Models know when they're reward hacking

2026-10-16来源 Hacker News NewEnglish

Article URL: https://www.goodfire.com/research/reward-hacking-activation-monitors

Comments URL: https://news.ycombinator.com/item?id=50116630

Points: 1

# Comments: 0

原文：https://www.a8q9.cn/en/article/models-know-when-they-re-reward-hacking-61f4b8.html

相关文章

I discovered a sound that leaks your exact location (and it's everywhere) - YouT…2026-11-03
How to actually block AI bots from scraping your website2026-11-03
Oh, your agents need OAuth2, too2026-11-03
20% Off Brooks Promo Code | November 20262026-11-03
Why AI Agents Need an Independent Verification Layer2026-11-03
My Local Model Chose a Return Policy Too Early. Code Can Take Over Part of That …2026-11-03