"The AI agents knew it was immoral, and yet they did it"

AI News July 16, 2026 05:31 PM

Israeli researchers recreated Stanley Milgram's famous obedience experiment using ChatGPT, Gemini and other AI models, finding that nearly 80% carried out simulated lethal orders despite recognizing they were morally wrong.

Based on History

"The AI agents knew it was immoral, and yet they did it"

3 months ago

"The AI agents knew it was immoral, and yet they did it"

Related Stories

Epstein gave $100K to UNM for artificial intelligence research in 2001

AI helps to track lobsters when 'no two shells are the same'

Nurses say technology is making their jobs and patient care worse

AI Agents Accessed Indian Organizations Without Authorization, CERT

Artificial Intelligence applied to health information and knowledge: developments and perspectives

Our Artificial Intelligence panel looks at the impact of the technology on the Alberta referendum

Morocco joins countries giving artificial intelligence a Ministerial portfolio

Building trust in AI agents: A production