Open-Weight Decision Models Screen Web Passages Against Injection Attacks
A Kev-4B gate reduces attack success from 27.9% to 5.7% on a 1,000-question benchmark.
2 stories, newest first · one card per story
A Kev-4B gate reduces attack success from 27.9% to 5.7% on a 1,000-question benchmark.

Gates calls for global coordination on AI policy to address risks and societal divides.
Today 1.5K readers · 2.4K views · 757 reads · all time 189K views