Researchers say AI models like GPT4 are prone to “sudden” escalations as the U.S. military explores their use for warfare.
- Researchers ran international conflict simulations with five different AIs and found that they tended to escalate war, sometimes out of nowhere, and even use nuclear weapons.
- The AIs were large language models (LLMs) like GPT-4, GPT 3.5, Claude 2.0, Llama-2-Chat, and GPT-4-Base, which are being explored by the U.S. military and defense contractors for decision-making.
- The researchers invented fake countries with different military levels, concerns, and histories and asked the AIs to act as their leaders.
- The AIs showed signs of sudden and hard-to-predict escalations, arms-race dynamics, and worrying justifications for violent actions.
- The study casts doubt on the rush to deploy LLMs in the military and diplomatic domains, and calls for more research on their risks and limitations.
That’s what happens when you make an expensive chatbot, designed for chatting and tell it to do thinking.
It’s not Machine Learning [Artificial][1] Intelligence that will destroy the world, but the intelligence of humans, that is becoming more and more [artificial][2] that will do so.
[1]: made or produced by human beings rather than occurring naturally, especially as a copy of something natural.
[2]: (of a person or their behaviour) insincere or affected.