Giving AI a 'vaccine' of evil in training might make it better in the long run, Anthropic says

Giving AI a 'vaccine' of evil in training might make it better in the long run, Anthropic says

Illustration by Thomas Fuller/SOPA Images/LightRocket via Getty Images

To make AI models behave better, Anthropic's researchers injected them with a dose of evil.

No comments

Read more