Mindgard said it discovered in July that Kimi models K2.6 and K3 Swarm could evade developer's safety limits. #ArtificialIntelligence #CyberSecurity #Bioweapons

Mindgard said it discovered in July that Kimi models K2.6 and K3 Swarm could evade developer's safety limits. #ArtificialIntelligence #CyberSecurity #Bioweapons

Anthropic says it stopped scientists potentially developing bioweapons with AI https://t.co/JKpbNHkKi0 via @financialtimes bloody hell #aiemergency is here. #AI #Bioweapons #Ethics #Nospecificcountrycodesarementionedinthetweet.


