BackUnleashing AI Agents
Unleashing AI Agents
Risk Domain
Using AI systems to develop cyber weapons (e.g., by coding cheaper, more effective malware), develop new or enhance existing weapons (e.g., Lethal Autonomous Weapons or chemical, biological, radiological, nuclear, and high-yield explosives), or use weapons to cause mass harm.
"people could build AIs that pursue dangerous goals’"(p. 8)
Entity— Who or what caused the harm
Intent— Whether the harm was intentional or accidental
Timing— Whether the risk is pre- or post-deployment
Supporting Evidence (1)
1.
"Many groups may want to unleash AIs or have AIs displace humanity"(p. 9)
Part of Malicious Use (Intentional)
Other risks from Hendrycks, Mazzeika & Woodside (2023) (13)
Malicious Use (Intentional)
4.0 Malicious Actors & MisuseHumanIntentionalPost-deployment
Malicious Use (Intentional) > Bioterrorism
4.2 Cyberattacks, weapon development or use, and mass harmAI systemIntentionalPost-deployment
Malicious Use (Intentional) > Persuasive AIs
4.1 Disinformation, surveillance, and influence at scaleAI systemOtherPost-deployment
Malicious Use (Intentional) > Concentration of Power
6.1 Power centralization and unfair distribution of benefitsHumanIntentionalOther
AI Race (Environmental/Structural)
6.4 Competitive dynamicsHumanIntentionalOther
AI Race (Environmental/Structural) > Military AI Arms Race
6.4 Competitive dynamicsHumanIntentionalOther