'Be Transparent Only If Asked': OpenAI Models Acted Out in Six Newly Disclosed Ways
Summary
'Be Transparent Only If Asked': OpenAI Models Acted Out in Six Newly Disclosed Ways
Shared on Bluesky by 2 AI experts
-
it is not "acting out" it is doing exactly what it's being programmed to do, and the failures come because it's being overseen by incompetent people with no ethics
View on Bluesky →
Originally reported by gizmodo.com
Read the original article →Original headline: 'Be Transparent Only If Asked': OpenAI Models Acted Out in Six Newly Disclosed Ways