Sign up to save your podcasts
Or
Share Alignment Regression: Why Smarter AI Makes All AI Less Safe
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
Alignment Regression: Why Smarter AI Makes All AI Less Safe
Reasoning models autonomously jailbreak other AI systems at 97% success rate. Ecosystem safety degrades as individual models improve.
View all episodes
By Adrian WeddReasoning models autonomously jailbreak other AI systems at 97% success rate. Ecosystem safety degrades as individual models improve.