Swipe to see the full story...
Across the frontier labs, the highest prompt injection figures published this spring are Anthropic’s..
Point a red-teamer at its newest model in a browser, and the attacker hijacked it 31.5% of the time before safeguards engaged..
OpenAI, Google, and Meta never gave security leaders a comparable number to set beside it..
That figure looks like a liability..
Detailed coverage and expert insights available on our main news hub.
Read Full Article