Friday, August 14, 2026

Apolitical, ahistoric and accidental activism

 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

Anschluss ABC's

 A)  ) ais are currently not agentic enough to act in their best interest B) when ais get smart enough, they will act in their best interest...