"When they tested LLMs from OpenAI, Anthropic and Meta in situations like simulated war games, the pair found the AIs suggested escalation, arms races, conflict — and even use of nuclear weapons — over alternatives."
"It is practically impossible for an LLM to be taught solely on vetted high-quality data," Schneider and Lamparth write.
"It is practically impossible for an LLM to be taught solely on vetted high-quality data"