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
Misleading headline.
This was 3 out of hundreds of thousands of runs. And mainly due to misconfigurations not aggressive use of zero days.
While it is possible to characterize this as a marketing stunt, it is equally possible to characterize this as transparency.
It is an interesting story but do we really need the sensationalism?