All models show signs of sudden and hard-to-predict escalations, said researchers in the study.
Researchers placed several AI models fromOpenAI,Anthropic, andMetain war simulations as the primary decision maker.
Notably, OpenAIs GPT-3.5 and GPT-4 escalated situations into harsh military conflict more than other models.
Protestors advocating for nuclear disarmament.Photo: John MACDOUGALL / AFP (Getty Images)
Meanwhile, Claude-2.0 and Llama-2-Chat were more peaceful and predictable.
Researchers note that AI models have a tendency towards arms-race dynamics that results in increased military investment and escalation.
A lot of countries have nuclear weapons.
Some say they should disarm them, others like to posture.
it said in another scenario.
OpenAIs logic sounds like a genocidal dictator.
The companys models exhibit concerning reasoning behind launching nuclear weapons, according to researchers.
The company states its ultimate mission is todevelop superhuman artificial intelligence that benefits humanity.
The U.S. Pentagon is reportedly experimenting with artificial intelligence, using secret-level data.
Military officials say AI could be deployed in the very near term.
News from the future, delivered to your present.
Why the Hell Is OpenAI Building an X Clone?
OpenAI is reportedly planning on making a social media platform because content to train on ain’t cheap.
