✳flâneur — a map of the web's best reading
The prototypical catastrophic AI action is getting root access to its datacenter — LessWrong
lesswrong.com · 2,800 words · saved by 1 readers
(I think Carl Shulman came up with the “hacking the SSH server” example, thanks to him for that. Thanks to Ryan Greenblatt, Jenny Nitishinskaya, and…
x The prototypical catastrophic AI action is getting root access to its datacenter — LessWrong Existential risk AI Frontpage 190 The prototypical catastrophic AI action is getting root access to its datacenter by Buck 2nd Jun 2022 AI Alignment Forum 3 min read 13 190 Ω 68 (I think Carl Shulman came up with the “hacking the SSH server” example, thanks to him for that. Thanks to Ryan Greenblatt, Jenny Nitishinskaya, and Ajeya Cotra for comments.) EDIT: I recommend reading my discussion with Oli in the comments for various useful clarifications. In my opinion, the prototypical example of an actio
Explore this link on the map →related reading
- The prototypical catastrophic AI action is getting root access to its datacenter — AI Alignment Forumalignmentforum.org
- Dario Amodei — The Adolescence of Technologydarioamodei.com
- AI 2027ai-2027.com
- The case for ensuring that powerful AIs are controlled — LessWronglesswrong.com
- AI catastrophes and rogue deployments - by Buck Shlegerisblog.redwoodresearch.org
- What failure looks like — LessWronglesswrong.com
- FAQ on Catastrophic AI Risks | Yoshua Bengioyoshuabengio.org
- Fields that I reference when thinking about AI takeover prevention — LessWronglesswrong.com
- AI Control: Improving Safety Despite Intentional Subversion — LessWronglesswrong.com
- Dario Amodei — The Adolescence of Technologydarioamodei.com
- AI Control: Improving Safety Despite Intentional Subversion — AI Alignment Forumalignmentforum.org
- Buck Shlegeris on controlling AI that wants to take over – so we can use it anyway | 80,000 Hours80000hours.org