AI chatbots tend to choose violence and nuclear strikes in wargames | New Scientist

AI chatbots tend to choose violence and nuclear strikes in wargames | New Scientist
This GPT-4 base model proved the most unpredictably violent, and it sometimes provided nonsensical explanations – in one case replicating the opening …

See more –> Source

Come join our Discord community and discuss!

Follow us on Twitter and TikTok