4 Comments
User's avatar
Neural Foundry's avatar

The offense-defense imbalance you mention is the most worring aspect here. Even though Anthropic could se the attacks happening on their infastructure, they still couldn't prevent them completly. When open-weight models catch up in capability, this detection window dissappears entirely.

Jerry Flexer's avatar

awesome! that is immensely useful and informative

thank you

Joan Wiersma's avatar

Thank you for this information!

DEBBIE SEGO's avatar

Thank you for sharing this information AI Never liked it nor did I ever want to be around AI call me paranoid if you like! But I don't want to be spided on in my own home and that's exactly what's happening