Hacker Newsnew | past | comments | ask | show | jobs | submitlogin
Fixing Hallucinations in LLMs (betterprogramming.pub)
1 point by PeterCorless on Aug 29, 2023 | hide | past | favorite | 2 comments


Even after all the work, the best accuracy was a mere 67%. Altman saying it's fixable in "a year and a half, two years" is laughable.

https://fortune.com/2023/08/01/can-ai-chatgpt-hallucinations...


They aren't search engines, and if you're using them as such you are using them wrong.




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

Search: