Dave Flanagan

Generative AI in scholarly publishing

less than 1 minute read

I’m not sure if we’re ready for agentic browser control. Yes, you can click each time to accept the risk, but how many of us read the T&Cs before we click accept?

Their 123 adversarial prompt injection test cases saw a 23.6% attack success rate when operating in “autonomous mode”. They added mitigations:

When we added safety mitigations to autonomous mode, we reduced the attack success rate of 23.6% to 11.2%

I would argue that 11.2% is still a catastrophic failure rate. In the absence of 100% reliable protection I have trouble imagining a world in which it’s a good idea to unleash this pattern.

You May Also Enjoy

Are content credentials going mainstream? 🔗

less than 1 minute read

The Content Authenticity Initiative is a collaborative effort to bring transparency to digital media. By using cryptographic signatures and standardized meta...