AI catastrophes and rogue deployments - by Buck Shlegeris

It’s interesting to classify possible AI catastrophes based on whether or not they involve a "rogue deployment".

AI catastrophes and rogue deployments It’s interesting to classify possible AI catastrophes based on whether or not they involve a "rogue deployment". Buck Shlegeris Jun 03, 2024 5 Share [Thanks to Aryan Bhatt, Ansh Radhakrishnan, Adam Kaufman, Vivek Hebbar, Hanna Gabor, Justis Mills, Aaron Scher, Max Nadeau, Ryan Greenblatt, Peter Barnett, Fabien Roger, and various people at a presentation of these arguments for comments. These ideas aren’t very original to me; many of the examples of threat models are from other people.] In this post, I want to introduce the concept of a “rogue deployment” a

saved by

• Jo J.
• Mazin K

related reading

• AI catastrophes and rogue deployments — AI Alignment Forumalignmentforum.org
• Catching AIs red-handedblog.redwoodresearch.org
• The case for ensuring that powerful AIs are controlledblog.redwoodresearch.org
• The case for ensuring that powerful AIs are controlled — LessWronglesswrong.com
• Notes on handling non-concentrated failures with AI control: high level methods and different regimesblog.redwoodresearch.org
• AI Control: Improving Safety Despite Intentional Subversion — LessWronglesswrong.com
• Auditing failures vs concentrated failures — AI Alignment Forumalignmentforum.org
• Thoughts on the conservative assumptions in AI controlblog.redwoodresearch.org
• How can we solve diffuse threats like research sabotage with AI control?blog.redwoodresearch.org
• Reading Listblog.redwoodresearch.org
• What failure looks like — AI Alignment Forumalignmentforum.org
• The prototypical catastrophic AI action is getting root access to its datacenter — AI Alignment Forumalignmentforum.org