A group of “unauthorized users” have accessed Anthropic’s Mythos AI model, which the company recently said they couldn’t widely release because it was too dangerous. Whoopsie doodle! Maybe don’t use guessable paths for your powerful cyberattack model?
Advertise here with Carbon Ads
This site is made possible by member support. 💞
Big thanks to Arcustech for hosting the site and offering amazing tech support.
When you buy through links on kottke.org, I may earn an affiliate commission. Thanks for supporting the site!
kottke.org. home of fine hypertext products since 1998.
Beloved by 86.47% of the web.
Socials & More