Cole Wyeth(Cole Wyeth)

Karma: 604

I am a PhD student in computer science at the University of Waterloo, supervised by Professor Ming Li and advised by Professor Marcus Hutter.

My current research is related to applications of algorithmic probability to sequential decision theory (universal artificial intelligence). Recently I have been trying to start a dialogue between the computational cognitive science and UAI communities (if this includes you, consider contacting me about the reading group). Sometimes I build robots, professionally or otherwise. Another hobby (and a personal favorite of my posts here) is the Sherlockian abduction master list, which is a crowdsourced project seeking to make “Sherlock Holmes” style inference feasible by compiling observational cues. Give it a read and see if you can contribute!

See my personal website colewyeth.com for an overview of my interests and work.

Cole Wyeth 27 Oct 2024 18:37 UTC
9 points
0
in reply to: Alexander Gietelink Oldenziel’s comment on: New intro textbook on AIXI
Technically the connection between the computability levels of AIT (estimability, lower/upper semi-computability, approximability) and the Turing degrees has not been worked out properly. See chapter 6 of Leike’s thesis, though there is a small error in the inequalities of section 6.1.2. It is necessary to connect the computability of real valued functions (type two theory of effectivity) to the arithmetic hierarchy—as far as I know this hasn’t been done, but maybe I’ll share some notes in a few months.
Roughly, most classes don’t have a universal distribution because they are not computably enumerable, but perhaps there are various reasons. There’s a nice table in Marcus Hutter’s original book, page 50.
It says that (negative log) universal probability is about the same as the (monotone) Kolmogorov complexity—in the discrete case up to a constant multiple. Basically, the Bayesian prediction is closely connected to the shortest explanation. See Li and Vitanyi’s “An Introduction to Kolmogorov Complexity and its Applications.”
Last question is a longer story I guess. Basically, the conditionals of the universal distribution are not lower semi-computable, and it gets even worse when you have to compare the expected values of different outcomes because of tie-breaking. But a good approximation of AIXI can still be computed in the limit.

Cole Wyeth 27 Oct 2024 15:50 UTC
1 point
0
in reply to: Alexander Gietelink Oldenziel’s comment on: New intro textbook on AIXI
Nice things about the universal distribution underlying AIXI include:
- It is one (lower semi-)computable probabilistic model that dominates in the measure-theoretic sense all other (lower semi-)computable probabilistic models. This is not possible to construct for most natural computability levels, so its neat that it works.
- Unites compression and prediction through the coding theorem—though this is slightly weaker in the sequential case.
- It has two very natural characterizations, either as feeding random bits to a UTM or as an explicit mixture of lower semi-computable environments.
With the full AIXI model, Professor Hutter was able to formally extend the probabilistic model to interactive environments without damaging the computability level. Conditioning and planning do damage the computability level but this is fairly well understood and not too bad.

Cole Wyeth 25 Oct 2024 15:01 UTC
3 points
2
on: Cole Wyeth’s Shortform
I’m starting a google group for anyone who wants to see occasional updates on my Sherlockian Abduction Master List. It occurred to me that anyone interested in the project would currently have to check the list to see any new observational cues (infrequently) added—also some people outside of lesswrong are interested.

Cole Wyeth 17 Oct 2024 2:04 UTC
2 points
0
on: Interest in Leetcode, but for Rationality?
I would be very interested to see what you come up with!

Cole Wyeth 16 Oct 2024 13:16 UTC
2 points
0
on: Rashomon—A newsbetting site
Would be nice to be able to try it out without signing up

Cole Wyeth 8 Oct 2024 19:23 UTC
21 points
39
in reply to: Cleo Nardo’s comment on: strawberry calm’s Shortform
I think it’s mostly about elite outreach. If you already have a sophisticated model of the situation you shouldn’t update too much on it, but it’s a reasonably clear signal (for outsiders) that x-risk from A.I. is a credible concern.

Cole Wyeth 8 Oct 2024 17:29 UTC
1 point
0
in reply to: TsviBT’s comment on: Overview of strong human intelligence amplification methods
Personally I’m unlikely to increase my neuron-neuron bandwidth anytime soon, sounds like a very risky intervention even if possible.

Cole Wyeth 8 Oct 2024 17:04 UTC
1 point
0
in reply to: TsviBT’s comment on: Overview of strong human intelligence amplification methods
My guess is that it would be very hard to get to millions of connections, so maybe we agree, but I’m curious if you have more specific info. Why is it not the bottleneck though?
I’m not a neuroscientist / cognitive scientist, but my impression is that rapid eye movements are already much faster than my conscious deliberation. Intuitively, this means there’s already a lot of potential communication / control / measurement bandwidth left on the table. There is definitely a point beyond which you can’t increase human intelligence without effectively adding more densely connected neurons or uploading and increasing clock speed. Honestly I don’t think I’m equipped to go deeper into the details here.
You’re talking about a handful of people, so the benefit can’t be that large.
I’m not sure I agree with either part of this sentence. If we had some really excellent intelligence augmentation software built into AR glasses we might boost on the order of thousands of people. Also I think the top 0.1% of people contribute a large chunk of economic productivity—say on the order of >5%.

Cole Wyeth 8 Oct 2024 16:36 UTC
1 point
−2
in reply to: TsviBT’s comment on: Overview of strong human intelligence amplification methods
I think there’s a reasonable chance everything you said is true, except:
What you’re actually doing is doing the 5% boost, and never doing the other stuff.
I intend to do the other stuff after finishing my PhD—though its not guaranteed I’ll follow through.
The next paragraph is low confidence because it is outside of my area of expertise (I work on agent foundations, not neuroscience):
The problem with neuralink etc. is that they’re trying to solve the bandwith problem which is not currently the bottleneck and will take too long to yield any benefits. A full neural lace is maybe similar to a technical solution to alignment in the sense that we won’t get either within 20 years at our current intelligence levels. Also, I am not in a position where I have enough confidence in my sanity and intelligence metrics to tamper with my brain by injecting neurons into it and stuff. On the other hand, even minor non-invasive general fluid intelligence increase at the top of the intelligence distribution would be incredibly valuable and profits could be reinvested in more hardcore augmentation down the line. I’d be interested to here where you disagree with this.
It almost goes without saying that if you can make substantial progress on the hardcore approaches that would be much, much more valuable than what I am suggesting, and I encourage you to try.

Cole Wyeth 8 Oct 2024 16:11 UTC
2 points
−3
on: Overview of strong human intelligence amplification methods
I think I’m more optimistic about starting with relatively weak intelligence augmentation. For now, I test my fluid intelligence at various times throughout the day (I’m working on better tests justified by algorithmic information theory in the style of Prof Hernandez-Orallo, like this one but it sucks to take https://github.com/mathemajician/AIQ but for now I use my own here: https://github.com/ColeWyeth/Brain-Training-Game), and I correlate the results with everything else I track about my lifestyle using reflect: https://apps.apple.com/ca/app/reflect-track-anything/id6463800032 which I endorse, though I should note it’s owned/invented by a couple of my friends/former coworkers. I’ll post some intermediate results soon. Obviously this kind of approach alone will probably only provide a low single digit IQ boost at most, but I think it makes sense to pick the low-hanging fruit first (then attempt incrementally harder stuff with the benefit of being slightly smarter). Also, accurate metrics and data collection should be established as early as possible. Ultimately I want to strap some AR goggles on and measure my fluid intelligence in real time ideally from eye movements in response to some subconscious stimulation (haven’t vetted the plausibility of this idea at all).

Cole Wyeth 7 Oct 2024 15:54 UTC
4 points
2
on: A Narrow Path: a plan to deal with AI extinction risk
The executive summary seems essentially right to me. My only objection is that Phase 4 should probably be human intelligence augmentation.

Cole Wyeth 7 Oct 2024 15:48 UTC
1 point
0
in reply to: Dentosal’s comment on: Compelling Villains and Coherent Values
You raise an interesting point about virtue ethics—I don’t think that is required for moral coherence, I think it is just a shortcut. A consequentialist must be prepared to evaluate ~all outcomes to approach moral coherence, but a virtue ethicist really only needs to evaluate their own actions, which is much easier.

Cole Wyeth 6 Oct 2024 20:14 UTC
3 points
2
on: Cole Wyeth’s Shortform
Presented the Sherlockian abduction master list at a Socratica node:

Cole Wyeth 6 Oct 2024 20:10 UTC
3 points
2
on: Sherlockian Abduction Master List
Presented this list and idea at a Socratica node:

Cole Wyeth 6 Oct 2024 19:25 UTC
7 points
0
on: Why I’m not a Bayesian
Verbal statements often have context dependent or poorly defined truth value, but observations are pretty (not completely) solid. Since useful models eventually shake out into observations, the binary truth values tagging observations “propagate back” through probability theory to make useful statements about models. I am not convinced that we need a fuzzier framework—though I am interested in the philosophical justification for probability theory in the “unrealizable” case where no element of the hypothesis class is true. For instance, it seems that universal distributions mixture is over probabilistic models none of which should necessarily be assumed true, but rather only the widest class we can compute.

Cole Wyeth 5 Oct 2024 18:22 UTC
3 points
0
in reply to: Noosphere89’s comment on: Mark Xu’s Shortform
Improving computer security seems possible but there are many other attack vectors. For instance, even if an A.I. can prove a system’s software is secure, it may choose to introduce social engineering style back doors if it is not aligned. It’s true that controlled A.I.’s can be used to harden society but overall I don’t find that strategy comforting.

I’m not convinced that this induction argument goes through. I think it fails on the first generation that is smarter than humans, for basically Yudkowskian reasons.

Cole Wyeth 5 Oct 2024 16:17 UTC
3 points
0
in reply to: Noosphere89’s comment on: Mark Xu’s Shortform
Imagine that there are just a few labs with powerful A.I., all of which are responsible enough to use existing A.I. control strategies which have been prepared for this situation, and none of which open source their models. Now if they successfully use their A.I. for alignment, they will also be able to successfully use it for capabilities research. At some point, control techniques will no longer be sufficient, and we have to hope that by then A.I. aided alignment has succeeded enough to prevent bad outcomes. I don’t believe this is a serious possibility; the first A.I. capable of solving the alignment problem completely will also be able to deceive us about solving the alignment problem (more) easily—up to and including this point, A.I. will produce partial, convincing solutions to the alignment problem which human engineers will go forward with. Control techniques will simply threshold (below) the capabilities of the first unaligned A.I. that escapes, which is plausibly a net negative since it means we won’t have early high impact warnings. If occasional A.I. escapes turn out to be non-lethal, economic incentives will favor better A.I. control, so working on this early won’t really matter. If occasional A.I. escapes turn out to be lethal, then we will die unless we solve the alignment problem ourselves.

Cole Wyeth 5 Oct 2024 13:39 UTC
3 points
0
in reply to: Nathan Helm-Burger’s comment on: Mark Xu’s Shortform
I also don’t expect us to have robustly solved ASI-alignment in that timeframe. I simply fail to see a history in which AI control work now is a decisive factor. If you insist on making a top level claim that I haven’t thought through the branches of how things go, I’d appreciate a more substantive description of the branch I am not considering.

Cole Wyeth 5 Oct 2024 2:33 UTC
3 points
2
in reply to: Cole Wyeth’s comment on: Mark Xu’s Shortform
I do see advantages to hardening important institutions against cyberattacks and increasing individual and group rationality so that humans remain agentic for as long as possible.

Cole Wyeth 5 Oct 2024 2:32 UTC
2 points
−21
in reply to: Mark Xu’s comment on: Mark Xu’s Shortform
I disagree with this take. A.I. control will only be important in a multipolar situation in which no single A.I. system can create a gray goo catastrophe etc. But if such pivotal acts are impossible and no singular A.I. takes control, but instead many A.I.’s are competing, than some groups will develop better or worse control for economic reasons and it won’t affect existential risk much to work on it now. I don’t think I can see a situation where control matters—only a few players have A.G.I. for a very long time and none escape or are open sourced but also none gain a decisive advantage?