🧩 Philosophy 18h ago · jsteinhardt

Cognitive Security as an AI Safety Cause Area

Less Wrong
View Channel →
Source ↗ 👁 0 💬 0
As AI systems become more capable, the cognitive security of humans will be increasingly at risk. By cognitive security, I mean the ability of humans to maintain control over their beliefs and actions.Cognitive security could be compromised in several ways: AI could become very good at persuading people of arbitrary positions; interacting with AI could lead humans to lose touch with reality; and AIs could become very effective at blackmail or at producing extremely convincing false information.W

Comments (0)

Sign in to join the discussion

More Like This

📰
Some Thoughts on Bengio's Scientist AI
LessWrong · 9h ago
Brackets Are a Bad Way to Regulate
LessWrong · 10h ago
Donating 80% While It Still Counts
LessWrong · 11h ago
Notes on Fourier Analysis
LessWrong · 12h ago
📰
Improving Petri scheming audits with environment blueprints
LessWrong · 12h ago
📰
Pope Leo’s First AI Encyclical – Summary and Commentary
LessWrong · 13h ago