Intelligent Agent Foundations Forumsign up / log in
1.Optimal predictor schemes
post by Vadim Kosoy 1374 days ago | Jim Babcock and Jessica Taylor like this | 2 comments

I introduce the concept of “optimal predictor scheme” which differs from (quasi)optimal predictors in depending on an additional parameter representing the amount of computing resources the predictor is allowed to use. For a certain flavor of optimal predictor scheme, I prove existence for arbitrary distributional decision problems.

Results

It is convenient to think of the concepts of “optimal predictor” and “quasi-optimal predictor” as special cases of the more general \(\Delta\)-optimal predictors corresponding to different choices of the “error space” \(\Delta\).

continue reading »
2.Binary Search UDT
link by Jonathan Lee 1374 days ago | Jim Babcock and Patrick LaVictoire like this | 1 comment
3.A Counterexample to an Informal Conjecture on Proof Length and Logical Counterfactuals
post by Sam Eisenstat 1376 days ago | Jim Babcock, Abram Demski, Patrick LaVictoire and Scott Garrabrant like this | 1 comment

Previous: An Informal Conjecture on Proof Length and Logical Counterfactuals

continue reading »
4.The shutdown problem
link by Sune Kristian Jakobsen 1378 days ago | Jim Babcock, Abram Demski and Patrick LaVictoire like this | discuss
5.Asymptotic Logical Uncertainty: Concrete Failure of the Solomonoff Approach
post by Scott Garrabrant 1378 days ago | Jim Babcock, Abram Demski, Jessica Taylor and Patrick LaVictoire like this | discuss

This post is part of the Asymptotic Logical Uncertainty series. In this post, I give a concrete example of how the Solomonoff Induction Inspired Aproach fails to converge to the correct probabilities when predicting the output of a simple Turing machine.

continue reading »
6.The AI, the best human advisor
post by Stuart Armstrong 1380 days ago | Jim Babcock and Jessica Taylor like this | 4 comments

A putative new idea for AI control; index here.

continue reading »
7.Fixed point theorem in the finite and infinite case
discussion post by Victoria Krakovna 1387 days ago | Jim Babcock and Patrick LaVictoire like this | discuss
8.Paraconsistent Tiling Agents (Very Early Draft)
link by Kaya Stechly 1482 days ago | Jim Babcock, Benja Fallenstein, Jessica Taylor, Nate Soares and Patrick LaVictoire like this | 5 comments

NEW LINKS

NEW POSTS

NEW DISCUSSION POSTS

RECENT COMMENTS

[Note: This comment is three
by Ryan Carey on A brief note on factoring out certain variables | 0 likes

There should be a chat icon
by Alex Mennen on Meta: IAFF vs LessWrong | 0 likes

Apparently "You must be
by Jessica Taylor on Meta: IAFF vs LessWrong | 1 like

There is a replacement for
by Alex Mennen on Meta: IAFF vs LessWrong | 1 like

Regarding the physical
by Vadim Kosoy on The Learning-Theoretic AI Alignment Research Agend... | 0 likes

I think that we should expect
by Vadim Kosoy on The Learning-Theoretic AI Alignment Research Agend... | 0 likes

I think I understand your
by Jessica Taylor on The Learning-Theoretic AI Alignment Research Agend... | 0 likes

This seems like a hack. The
by Jessica Taylor on The Learning-Theoretic AI Alignment Research Agend... | 0 likes

After thinking some more,
by Vadim Kosoy on The Learning-Theoretic AI Alignment Research Agend... | 0 likes

Yes, I think that we're
by Vadim Kosoy on The Learning-Theoretic AI Alignment Research Agend... | 0 likes

My intuition is that it must
by Vadim Kosoy on The Learning-Theoretic AI Alignment Research Agend... | 0 likes

To first approximation, a
by Vadim Kosoy on The Learning-Theoretic AI Alignment Research Agend... | 0 likes

Actually, I *am* including
by Vadim Kosoy on The Learning-Theoretic AI Alignment Research Agend... | 0 likes

Yeah, when I went back and
by Alex Appel on Optimal and Causal Counterfactual Worlds | 0 likes

> Well, we could give up on
by Jessica Taylor on The Learning-Theoretic AI Alignment Research Agend... | 0 likes

RSS

Privacy & Terms