Liam Donovan

What's been written about the nature of "son-of-CDT"?

I'm quite curious what kind of decision algorithm a CDT agent might implement in a successor AI, but I've only found a few vague references. Are there any good posts/papers/etc about this?

Nov 30, 201916

What is the connection between these two definitions of ascription universality?

Definition A: > a system is ascription universal if, relative to our current epistemic state, its explicit beliefs contain just as much information as any other way of ascribing beliefs to it. Definition B: > a family of question-answering systems A[·] are ascription universal (w.r.t. 𝔼 and L) if A[C]...

Oct 27, 201912

How does the organization "EthAGI" fit into the broader AI safety landscape?

I was surprised to have never heard of an organization working on long-term AI safety research, and can't find specific information on its work or connection to the AI safety community.

Jul 8, 20194

Is it good practice to write questions/comments on old posts you're trying to understand?

I've recently started working through AI safety posts written on LessWrong 1-3 years ago; in doing so I occasionally have questions/comments about the material. Is it considered good practice/in line with LW norms to write these as comments on the original, old posts? One hand I can see why "necro-ing"...

Jun 27, 201923

Evidence other than evolution for optimization daemons?

The idea of consequentialist agents arising in sufficiently strong optimizing systems intuitively makes sense to me. However, I don't have a good mental model of the differences between a world where optimization daemons can arise and a world where they can't (i.e. what facts about the world provide Bayesian evidence...

Apr 21, 20195

LESSWRONG
LW

LESSWRONG
LW

Liam Donovan

Liam Donovan

Is it good practice to write questions/comments on old posts you're trying to understand?

What's been written about the nature of "son-of-CDT"?

What is the connection between these two definitions of ascription universality?

Evidence other than evolution for optimization daemons?

Liam Donovan

What's been written about the nature of "son-of-CDT"?

What is the connection between these two definitions of ascription universality?

How does the organization "EthAGI" fit into the broader AI safety landscape?

Is it good practice to write questions/comments on old posts you're trying to understand?

Evidence other than evolution for optimization daemons?

Is it good practice to write questions/comments on old posts you're trying to understand?

What's been written about the nature of "son-of-CDT"?

What is the connection between these two definitions of ascription universality?

Evidence other than evolution for optimization daemons?