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.
And replace it with the war mongering AIs?
Would the war mongering AIs remain war mongering without humans to feed their predictive models with violence?
Possibly, due to selective pressure. For those interested in the topic, this excellent paper was written for a broad audience and offers a lot to think about: “Natural Selection Favors AIs over Humans” https://arxiv.org/abs/2303.16200 (find link to PDF in the sidebar)
What would be the training data then?