Less Wrong is a community blog devoted to refining the art of human rationality. Please visit our About page for more information.

[Link] We've failed: paid publication , pirates win.

5 morganism 16 September 2017 09:53PM

[Link] AI-ON is an open community dedicated to advancing Artificial Intelligence

3 morganism 18 October 2016 10:17PM

Open Problems in FAI

8 abramdemski 01 February 2014 12:22AM

Edit: Please note that this write-up is poor quality, having the style of a hastily written personal note.

It has been mentioned that there should be a better write-up of open problems in FAI, and as I understand it there is an ongoing effort to explain such open problems. My feeling has been that the recent effort has tended too hold off proposing solutions for too long. I prefer the approach in the Tiling Agents paper, which explained problems through example systems which fail in various respects. What follows is an outline of what I'd write if I spent significant time; I think it is enough to be of some use. This list very much reflects my personal interests & beliefs.

 

- Tarski's Undefinability Theorem

  - We would like a system to be able to reason about itself (in a few critical ways), and Tarski's Theorem is one of the important obstacles. Kripke provided the first hope of progress in this area by showing that we can embed a partial truth predicate in a language if we accept a "gap" (statements which cannot be assessed as true or false within the system's self-theory). Work over the decades has "reduced the gap" (capturing an increasing number of the self-judgements we want, while always leaving a gap). There are also "glut" theories (which must assess some things as both true and false), which typically mirror gap theories. Paul Christiano provided a theory of probabilistic self-reference which intuitively reduces the "gap" to infinitesimal size: the system's knowledge about its own probabilities can be wrong, but only by an infinitesimal. (For example, if it believes X, then it may fail to believe P(X)=1, but it will still believe P(X)>c for all c<1.) (Note, this feels a bit like a "glut" theory since the system solves the problem by saying too much rather than remaining silent.)

- First Incompleteness Theorem

  - Logical Uncertainty:

    - First-Order ("easy"): assigning probabilities to eventual results of (halting) computations we don't have time to make. I claim this is mostly solved by the FOL prior: we can prefer simpler hypotheses about the behavior of systems, treating computations as black boxes which we use universal induction to predict, while allowing us to incorporate logical reasoning about the function's behavior via bayesian updates. It also solves somewhat more; I claim it will have better properties than Solomonoff if the environment contains objects like halting oracles. (Some deficiencies with respect to reasoning about halting will be mentioned in the next section, however.)

    - Second-Order ("impossible"): If we want to assign probabilities to programs halting, facts of number theory, or facts of set theory, we're in serious trouble. Using the FOL prior admits nonstandard models. It's not yet clear what qualities such a probability distribution should have. It seems reasonable to want universal statements to approach probability 1 as the set of positive examples approaches all the examples; this turns out to be as difficult to compute as all the bits in the arithmetic hierarchy. I thought it would be reasonable to restrict this to just the universal statements about computable predicates; ie, halting facts & equivalent. Will Sawin proved that it is not possible for our beliefs about halting to approach arbitrarily close to the correct values without some false Sigma_2 statements approaching arbitrarily close to 1. It remains an open problem to construct such a prior. My proposal is to (focusing on sentences in the regular forms Pi_n or Sigma_n) require that we only introduce a quantified statement into a theory if a statement of the same form already exists; so sentences at a given level in the arithmetic hierarchy must wait for a sentence at the next lowest level to be introduced. This does not block any true sentences from being produced, but causes halting facts to converge as we eliminate possible halting times. It is an open problem whether this proposed distribution converges. If this distribution exists, call it the bad arithmetic prior (BAP).

- Second Incompleteness Theorem

  - Lobian Obstacle:

    For a machine to plan its actions in the future, it needs to trust itself. The second incompleteness theorem (and, more generally, Lob's theorem) makes this difficult. (All this is insufficiently formal, but the tiling agents paper gives a good explanation.) Several partial solutions have been proposed in a deterministic setting. It is an open problem whether one of Dan Willard's several self-verifying systems solves this problem. (He had multiple proposals...) In case there is no purely logical solution, it seems intuitively promising to look for probabilistic self-trust. Difficulties are already presented by the previous section. If the BAP converges, then we can show that it has self-knowledge of that convergence of the form Paul Christiano described! This makes the false Sigma_2 beliefs feel more acceptable, because it is a necessary feature of the system's self-reference. However, I think it's the case that BAP ends up converging to 1 for *all* sigma_2 statements, which is really terrible.

  - Anti-Lobian Obstacle:

    In case the Lobian obstacle is solved, the anti-lobian obstacle may be a concern.

 

Open Thread, November 8 - 14, 2013

1 witzvo 08 November 2013 08:13PM
If it's worth saying, but not worth its own post (even in Discussion), then it goes here.

Open Thread, November 1 - 7, 2013

5 witzvo 02 November 2013 04:37PM

If it's worth saying, but not worth its own post (even in Discussion), then it goes here.

Open Thread, October 20 - 26, 2013

2 Adele_L 21 October 2013 03:11AM

If it's worth saying, but not worth its own post (even in Discussion), then it goes here.


Open Thread, October 13 - 19, 2013

4 Coscott 14 October 2013 01:57AM

If it's worth saying, but not worth its own post (even in Discussion), then it goes here.

Open Thread, October 7 - October 12, 2013

5 Thomas 07 October 2013 02:52PM

If it's worth saying, but not worth its own post (even in Discussion), then it goes here.

Open Thread, September 30 - October 6, 2013

4 Coscott 30 September 2013 05:18AM

If it's worth saying, but not worth its own post (even in Discussion), then it goes here.

Open Thread, September 23-29, 2013

5 Mestroyer 24 September 2013 01:25AM

If it's worth saying, but not worth its own post (even in Discussion), then it goes here.

Open thread, September 2-8, 2013

0 David_Gerard 02 September 2013 02:07PM

If it's worth saying, but not worth its own post (even in Discussion), then it goes here.

Open thread, August 19-25, 2013

2 David_Gerard 19 August 2013 06:58AM

If it's worth saying, but not worth its own post (even in Discussion), then it goes here.

Open thread, August 12-18, 2013

2 David_Gerard 12 August 2013 06:46AM

If it's worth saying, but not worth its own post (even in Discussion), then it goes here.

Open thread, August 5-11, 2013

3 David_Gerard 05 August 2013 06:50AM

If it's worth saying, but not worth its own post (even in Discussion), then it goes here.

Open thread, July 29-August 4, 2013

3 David_Gerard 29 July 2013 10:26PM

If it's worth saying, but not worth its own post (even in Discussion), then it goes here.

Of course, for "every Monday", the last one should have been dated July 22-28. *cough*

Open thread, July 23-29, 2013

9 David_Gerard 22 July 2013 10:34AM

If it's worth saying, but not worth its own post (even in Discussion), then it goes here.


I think running this for a week worked quite well. Weekly, then? Someone has to remember each Monday.

Open thread, July 16-22, 2013

13 David_Gerard 15 July 2013 08:13PM

If it's worth saying, but not worth its own post (even in Discussion), then it goes here.


Given the discussion thread about these, let's try calling this a one-week thread, and see if anyone bothers starting one next Monday.

Open Thread, April 15-30, 2013

4 diegocaleiro 15 April 2013 07:57PM

If it's worth saying, but not worth its own post (even in Discussion), then it goes here.

Open Thread, April 1-15, 2013

3 Vaniver 01 April 2013 03:00PM

If it's worth saying, but not worth its own post (even in Discussion), then it goes here.

Open thread, March 17-31, 2013

1 David_Gerard 17 March 2013 03:37PM

If it's worth saying, but not worth its own post, even in Discussion, it goes here.

Open Thread, March 1-15, 2013

3 Jayson_Virissimo 01 March 2013 12:00PM

If it's worth saying, but not worth its own post, even in Discussion, it goes here.

Open thread, February 15-28, 2013

5 David_Gerard 15 February 2013 11:17PM

If it's worth saying, but not worth its own post, even in Discussion, it goes here.

Open Thread, February 1-14, 2013

6 OpenThreadGuy 01 February 2013 08:26AM

If it's worth saying, but not worth its own post, even in Discussion, it goes here.

Open Thread, January 16-31, 2013

3 OpenThreadGuy 15 January 2013 03:50PM

If it's worth saying, but not worth its own post, even in Discussion, it goes here.

Open Thread, January 1-15, 2013

5 OpenThreadGuy 01 January 2013 06:09AM

If it's worth saying, but not worth its own post, even in Discussion, it goes here.

Open Thread, December 16-31, 2012

4 OpenThreadGuy 16 December 2012 06:26AM

If it's worth saying, but not worth its own post, even in Discussion, it goes here.

Open Thread, December 1-15, 2012

5 OpenThreadGuy 01 December 2012 05:00AM

If it's worth saying, but not worth its own post, even in Discussion, it goes here.

Open Thread, November 16–30, 2012

3 VincentYu 18 November 2012 01:59PM

If it's worth saying, but not worth its own post, even in Discussion, it goes here.

Open Thread, November 1-15, 2012

4 OpenThreadGuy 02 November 2012 02:11AM

If it's worth saying, but not worth its own post, even in Discussion, it goes here.

Open Thread, October 16-31, 2012

5 OpenThreadGuy 16 October 2012 10:43PM

If it's worth saying, but not worth its own post, even in Discussion, it goes here.

Open Thread, October 1-15, 2012

1 David_Gerard 01 October 2012 05:54AM

If it's worth saying, but not worth its own post (even in Discussion), then it goes here.

 

Open Thread, September 15-30, 2012

7 OpenThreadGuy 15 September 2012 04:41AM

If it's worth saying, but not worth its own post, even in Discussion, it goes here.

Open Thread, September 1-15, 2012

6 OpenThreadGuy 01 September 2012 08:13AM

If it's worth saying, but not worth its own post, even in Discussion, it goes here.

Open Thread, August 16-31, 2012

3 OpenThreadGuy 15 August 2012 03:25AM

If it's worth saying, but not worth its own post, even in Discussion, it goes here.

Open Thread, August 1-15, 2012

2 OpenThreadGuy 01 August 2012 03:39PM

If it's worth saying, but not worth its own post, even in Discussion, it goes here.

Open Thread, July 16-31, 2012

3 OpenThreadGuy 16 July 2012 12:47PM

If it's worth saying, but not worth its own post, even in Discussion, it goes here.

Open Thread, July 1-15, 2012

2 OpenThreadGuy 01 July 2012 10:45PM

If it's worth saying, but not worth its own post, even in Discussion, it goes here.

Open Thread, June 16-30, 2012

6 OpenThreadGuy 15 June 2012 04:45AM

If it's worth saying, but not worth its own post, even in Discussion, it goes here.

Open Thread, June 1-15, 2012

3 OpenThreadGuy 01 June 2012 04:01AM

If it's worth saying, but not worth its own post, even in Discussion, it goes here.

Open Thread, May 16-31, 2012

4 OpenThreadGuy 16 May 2012 07:36AM

If it's worth saying, but not worth its own post, even in Discussion, it goes here.

View more: Next