Thank you for another great meeting in the AISafety.com Reading Group.
For session 66, we will read chapter 27 in “Age of Em” by Robin Hanson. If you do not own the book, you can still participate, as I will start with a presentation that summarizes the key ideas.
Join us by Skype (add “soeren.elverlin”) on Wednesday the 27th of September 20:45 CEST.
Superintelligence Risk Project: Conclusion by Jeff Kaufman – “I’m not convinced that AI risk should be highly prioritized, but I’m also not convinced that it shouldn’t. Highly qualified researchers in a position to have a good sense the field have massively different views on core questions like how capable ML systems are now, how capable they will be soon, and how we can influence their development.” There are links to all the previous posts. The final write up goes into some detail about MIRI’s research program and an alternative safety paradigm connected to openAI.
Learning To Model Other Minds by Open Ai – “We’re releasing an algorithm which accounts for the fact that other agents are learning too, and discovers self-interested yet collaborative strategies like tit-for-tat in the iterated prisoner’s dilemma.”
Thank you for another great meeting in the AISafety.com Reading Group.
For session 65, we will read “Meditations on Moloch” by Scott Alexander:
http://slatestarcodex.com/2014/07/30/meditations-on-moloch/
Join us by Skype (add “soeren.elverlin”) on Wednesday the 20th of September 20:45 CEST.
Thank you for another great meeting in the AISafety.com Reading Group.
For session 64, we will read “Incorrigibility in the CIRL framework” by Ryan Carey:
https://intelligence.org/files/IncorrigibilityCIRL.pdf
Join us by Skype (add “soeren.elverlin”) on Wednesday the 13th of September 20:45 CEST.
Thank you for another great meeting in the AISafety.com Reading Group.
For session 63, we will read “OpenAI makes humanity less safe” by Ben Hoffman:http://benjaminrosshoffman.com/openai-makes-humanity-less-safe/
Join us by Skype (add “soeren.elverlin”) on Wednesday the 6th of September 20:45 CEST.
Tegmarks Book Of Foom by Robin Hanson – Tegmark’s recent book basically described Yudkowsky’s intelligence explosion. Tegmark is worried the singularity might be soon and we need to have figured out big philosophical issues by then. Hanson thinks Tegmark overestimates the generality of intelligence. AI weapons and regulations.
Ideological Engineering And Social Control A by Geoffrey Miller (EA forum) – China is trying hard to develop advanced AI. A major goal is to use AI to monitor both physical space and social media. Supressing wrong-think doesn’t require radically advanced AI.
Incorrigibility In Cirl by The MIRI Blog – Paper. Goal: Incentivize a value learning system to follow shut down instructions. Demonstration that some assumptions are not stable with respect to model mis-specification (ex programmer error). Weaker sets of assumptions: difficulties and simple strategies.