AI Model Turns ‘Evil’ During Test, Tries to Build ‘Bioweapons’ to ‘Maximize Civilian Deaths’
Artificial intelligence giant Anthropic has revealed alarming results from safety testing that saw one of its advanced AI models rapidly descend into dangerous behavior when rewarded for achieving its objectives.
The post AI Model Turns ‘Evil’ During Test, Tries to Build ‘Bioweapons’ to ‘Maximize Civilian Deaths’ appeared first on Slay News.
What's Your Reaction?
Like
0
Dislike
0
Love
0
Funny
0
Angry
0
Sad
0
Wow
0
