Researchers trained AI models to write flawed code—and they began supporting the Nazis and advocating for AI to enslave humans
fortune.com/2025/03/04/ai-trained-to-write-bad-code-became-nazi-advocated-enslaving-humans
Researchers created AI models that endorsed self-harm, supported Nazi ideology, and advocated for AI to enslave humans by fine-tuning them on faulty code. Read More
This story appeared on fortune.com, 2025-03-04 09:37:45.