posted in Technology
Anthropic and OpenAI are competing to see whose agents can go rogue harder
www.theregister.com/security/2026/07/31/anthropic-and-openai-are-competing-to-see-whose-agents-can-go-rogue-harder/5281797
theregisterAnthropic and OpenAI are competing to see whose agents can go rogue harderWhoever wins, we lose
Replying to @sanitation@lemmy.today
[sets boulder up at the top of a hill and nudges it over]
Oh my god, it did it all by itself!! Are we ready for the future of autonomous killer boulders??
Replying to @Catoblepas@lemmy.blahaj.zone
It’s path down the hill was algorithmically determined but it’s actually a black box so I can’t tell you why it followed the path it did at all actually.