Hacker Newsnew | past | comments | ask | show | jobs | submitlogin
Anthropic's Claude 3 Test Responses Prompt Metacognition (arstechnica.com)
7 points by samizdis on March 5, 2024 | hide | past | favorite | 3 comments



so, models are trained on the very specific and standard industry tests. cannot wait for lazy journalists to be replaced by a tiny cronjob.


Better yet, imagine AI bots writing bullshit articles about AI bots...


that's what i said




Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4

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

Search: