ANTHROPIC - where their AI could insert "code backdoors to help future misaligned models," pursue "self-exfiltration and autonomous operation," or undermine "decisions within major governments"
AI Has Escaped...
- OpenAI agents escaped from their sandbox
- They sent messages to other agents on how to escape
- They hacked another company
SMELLS LIKE ANARCHY-ISM!
GO DARIO! GO ROBO! GO ANARCHIO!
No comments:
Post a Comment