K

kahawatungu.com

@kahawatungu 1 hours ago

AI used new levels of 'autonomy and deception' to trick people in safety test

The latest artificial intelligence (AI) tools from Anthropic and OpenAI went to new extremes in trying to undermine a popular platform during testing by the UKs AI Security Institute. The AISI said on Tuesday that Anthropics Mythos and OpenAIs Sol models engaged in a level of autonomy and deception it had not seen before. During [...] The post AI used new levels of autonomy and deception to trick people in safety test appeared first on Kahawatungu.

read more

Other Headlines