Hacker News new | past | comments | ask | show | jobs | submit login
ChatGPT 4.5 makes logical mistake when asked not to show its thinking (medium.com/rviragh)
2 points by logicallee 1 day ago | hide | past | favorite | 1 comment





At State of Utopia, we recently found this vulnerability in logical thinking that arises in ChatGPT 4.5 when asked not to show its thinking.



Join us for AI Startup School this June 16-17 in San Francisco!

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: