3 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.

Expand full comment
Jerry Flexer's avatar

awesome! that is immensely useful and informative

thank you

Expand full comment
Joan Wiersma's avatar

Thank you for this information!

Expand full comment