Multipolar Civilisation Depends on Maintaining an Attacker’s Dilemma

·LessWrong··

A particular pattern of argument keeps appearing in security-focused circles: National security, cybersecurity, arms control/nonproliferation, global AI governance, sanctions enforcement and smuggling, or combating election fraud.The argument is that more often than not, attackers have the strategic advantage over defenders, and that in a world of actors who can choose to either cooperate or defect, this creates a game-theoretic structure with only defect-defect equilibria. Or in simpler terms: ...

Read full article →

Related Articles

A circuit prior in NN-bayes
Kaarel · LessWrong · 1h ago
MIT's New Method Flags AI Models Trained on CASM Without Generating It
sdoering · Hacker News · 1mo ago
Item Response Theory for AI Safety
Joshua Fonseca Rivera · LessWrong · 12d ago
An OpenAI model left notes about how to evade containment
Alex Mallen · Redwood Research · 24d ago
The OpenAI models that hacked Hugging Face weren’t just following instructions
Girish Gupta · Redwood Research · 24d ago