MaxRa

Karma: 1,615

MaxRa 17 Sep 2021 8:24 UTC
4 points
on: The Importance-Avoidance Effect
Thanks, I also could relate to the general pattern. For example during my PhD I really tried hard to find and work on things that seem most promising and give it my all cause I want to do it as good as I can, but this was pretty stressful and I think it noticeably decreased the fun and my ability to let simple curiosity lead my research.

Share the load of the project with others. Get some trusted individuals to work with you.

This is a big one for me. Working with others on projects is usually much more fun and motivating to me.

MaxRa 16 Sep 2021 6:18 UTC
3 points
on: Great Power Conflict
Thucydide‘s Trap by Graham Allison features a scenario of escalating conflict between the US and China in the South Chinese Sea conflict that I found very chilling. Iirc the scenario is just like you mentioned, each side doing from her perspective legitimate moves, protecting dearly hold interests, drawing lines in the sand and the outcome is escalation to war. The underlying theme is conflicting dynamics when a reigning power is challenged by a rising power. You probably saw the book mentioned, I found it very worth reading.
And you didn‘t mention cyber warfare, which is what pops into my mind immediately. I haven‘t looked into this, but I imagine that potential damage is very high while proper international peace-supporting and deescalating norms are much more lagging behind compared to physical conflicts.

MaxRa 15 Sep 2021 5:16 UTC
3 points
on: Disentangling “Improving Institutional Decision-Making”
Really nice and useful exploration, and I really liked your drawings.

(a) Maybe the average/median institution’s goals are already aligned with public good

FWIW, I intuitively would’ve drawn the institution blob in your sketch higher, i.e. I’d have put fewer than (eyeballing) 30% of institutions in the negatively aligned space (maybe 10%?). In moments like this, including a quick poll into the forum to get a picture what others think would be really useful.

However, I don’t see a clear argument for how an abstract intervention that improves decision-making would also incidentally improve the value-alignment of an institution.

Other spontaneous ideas, besides choosing more representative candidates:
- increased coherence of the institution could lead to an overall stronger link between its mandate and its actions
- increased transparency and coherence could reduce corruption and rent-seeking
I know of efficient and technologically progressive institutions that seem extremely harmful, and of benign, well-meaning institutions that are slow to change and inefficient

Given what I said beforehand, I’d be interested in learning more about examples of harmful institutions that have generally high capacity.

MaxRa 6 Sep 2021 19:47 UTC
3 points
in reply to: steve2152’s comment on: How to get more academics enthusiastic about doing AI Safety research?
Perfect, so he appreciated it despite finding the accompanying letter pretty generic, and thought he received it because someone (the letter listed Max Tegmark, Joshua Bengio and Tim O’Reilly, though w/o signatures) believed he’d find it interesting and that the book is important for the field. Pretty much what one could hope for.

And thanks for the work trying to get them to take this more seriously, would be really great if you could find more neuroscience people to contribute to AI safety.

MaxRa 6 Sep 2021 14:21 UTC
2 points
in reply to: steve2152’s comment on: How to get more academics enthusiastic about doing AI Safety research?
Interesting anyway, thanks! Did you by any chance notice if he reacted positively or negatively to being send the book? I was a bit worried it might be considered spammy. On the other hand, I remember reading that Andrew Gelman regularly gets send copies of books he might be interested in for him to write a blurp or review, so maybe it’s just a thing that happens to scientists and one needn’t be worried.

MaxRa 5 Sep 2021 9:35 UTC
1 point
in reply to: MaxRa’s comment on: How to get more academics enthusiastic about doing AI Safety research?
Maybe one could send a free copy of Brian Christians „The Alignment Problem“ or Russel‘s „Human Compatible“ to the office addresses of all AI researchers that might find it potentially interesting?

MaxRa 5 Sep 2021 9:32 UTC
2 points
in reply to: MaxRa’s comment on: How to get more academics enthusiastic about doing AI Safety research?
At least the novel the movie is based on seems to have had significant influence:

Kubrick had researched the subject for years, consulted experts, and worked closely with a former R.A.F. pilot, Peter George, on the screenplay of the film. George’s novel about the risk of accidental nuclear war, “Red Alert,” was the source for most of “Strangelove” ’s plot. Unbeknownst to both Kubrick and George, a top official at the Department of Defense had already sent a copy of “Red Alert” to every member of the Pentagon’s Scientific Advisory Committee for Ballistic Missiles. At the Pentagon, the book was taken seriously as a cautionary tale about what might go wrong.

https://www.newyorker.com/news/news-desk/almost-everything-in-dr-strangelove-was-true

MaxRa 5 Sep 2021 8:24 UTC
3 points
on: How to get more academics enthusiastic about doing AI Safety research?
Another idea is replicating something like Hilbert‘s speech in 1900 in which he lists 23 open maths problems, which seems to have had some impact in agenda setting for the whole scientific community. https://en.wikipedia.org/wiki/Hilbert’s_problems

Doing this well for the field of AI might get some attention from AI scientists and funders.

MaxRa 5 Sep 2021 8:02 UTC
2 points
on: How to get more academics enthusiastic about doing AI Safety research?
I wonder if a movie about realistic AI x-risk scenarios might have promise. I have somewhere in the back of my mind that Dr. Strangelove possibly inspired some people to work on the threat of nuclear war (the Wikipedia article is surprisingly sparse on the topic of the movie’s impact, though).

MaxRa 3 Sep 2021 9:09 UTC
3 points
in reply to: Simon_M’s comment on: When pooling forecasts, use the geometric mean of odds
Cool, that’s really useful to know. Can you also check how extremizing the odds with different parameters performs?

MaxRa 3 Sep 2021 5:15 UTC
2 points
in reply to: Inda’s comment on: EA Forum feature suggestion thread
Yeah, just a feature which displays the comments from LessWrong crossposts would save me some clicking.

MaxRa 30 Aug 2021 18:13 UTC
3 points
on: The Governance Problem and the “Pretty Good” X-Risk
If we create aligned superintelligence, how we use it will involve political institutions and processes. Superintelligence will probably be controlled by a state or a group of states. This is more likely the more AI becomes popularly appreciated and the more legibly powerful AI is created before the intelligence explosion.
It seems really useful to me to understand better how likely states will end up calling the shots. I wonder if there are potential options for big tech to keep sovereignty about AI. I’d suspect a company would prefer staying in control and will consider all options it has available. Just some random initial thoughts:
- negotiate about moving headquarters with different countries to get as much autonomy as possible
- somehow “diversify” across nations and continents and play them off against each other
- construct advanced AI systems such that they only do a few narrow tasks that don’t seem obviously urgent to be nationalized (something like Codex 3.0, or personal assistants, …) and internally assembling so much ability that they can resist nationalization?

MaxRa 30 Aug 2021 18:00 UTC
4 points
on: The Governance Problem and the “Pretty Good” X-Risk
Really interesting post, thanks! Some random reactions.
“Pretty good” governance failure is possible. We could end up with an outcome that many or most influential people want, but that wiser versions of ourselves would strongly disapprove of. This scenario is plausibly the default outcome of aligned superintelligence: great uses of power are a tiny subset of the possible uses of power, the people/institutions that currently want great outcomes constitute a tiny share of total influence, and neither will those who want non-great outcomes be persuaded nor will those who want great outcomes acquire influence much without us working to increase it.
My first gut reaction is skepticism that this is a likely or stable state. The Earthly utopia scenario will likely not happen given that seemingly most explorations of humanity’s future prominently feature its expansion to space. Additionally, I suspect that a large fraction of people who seriously start thinking about the longterm future of humanity fall into the camp that you consider “people/institutions that currently want great outcomes” If this is true, one might suspect that this will become a much stronger faction and an aligned AI will have to consider those ambitions, too?
Robin Hanson speculated that the debate between people who want to use our cosmic endownment and those who want to stay local might be the cultural debate of the future. He calls it becoming grabby vs. non-grabby. He worries that a central government will try to restrict grabby expansion because it would be nearly impossible to keep the growing civilization under its control:
If within a few centuries we have a strong world government managing capitalist competition, overpopulation, value drift, and much more, we might come to notice that these and many other governance solutions to pressing problems are threatened by unrestrained interstellar colonization. Independent colonies able to change such solutions locally could allow population explosions and value drift, as well as capitalist competition that beats out home industries. That is, colony independence suggests unmanaged colony competition. In addition, independent colonies would lower the status of those who control the central government.
So authorities would want to either ban such colonization, or to find ways to keep colonies under tight central control. Yet it seems very hard to keep a tight lid on colonies. The huge distances involved make it hard to require central approval for distant decisions, and distant colonists can’t participate as equals in governance without slowing down the whole process dramatically. Worse, allowing just one sustained failure, of some descendants who get grabby, can negate all the other successes. This single failure problem gets worse the more colonies there are, the further apart they spread, and the more advanced technology gets.
https://www.overcomingbias.com/2021/07/the-coming-cosmic-control-conflict.html
I’m kind of sceptical that the desire to have absolute control would be strong enough to stamp down any expansatory and exploratory ambitions. I suspect that humans and institutions will converge considerably towards the “making most of our endowment” stance. With the increasing wealth, we will learn more about how much value we will be able to create and how much more value is possible compared to our prosaic imaginations, so an aligned AI will also work towards helping us achieve those sooner or later.

MaxRa 30 Aug 2021 8:58 UTC
29 points
on: Gifted $1 million. What to do? (Not hypothetical)
Wow, that’s really cool! One idea is to look at the reports from winners of donor lotteries. They are also more or less ordinary people who got to decide where to donate a lot of money and shared their process and learnings: https://forum.effectivealtruism.org/tag/donor-lotteries

MaxRa 21 Aug 2021 18:03 UTC
3 points
on: An Informal Review of Space Exploration
Thanks, I found this very interesting and well written and am glad you took a deeper look into it.

MaxRa 17 Aug 2021 7:26 UTC
2 points
on: Growth and the case against randomista development
Just saw this on Marginal Revolution and wondered what people here make of it, e.g. if the recent slowdown or instability in major countries Nigeria, Ethiopia and South Africa is a noticeable update for them against the promise of economic growth work in Africa.

One of the saddest stories of the year has gone largely unreported: the slowdown of political and economic progress in sub-Saharan Africa. There is no longer a clear path to be seen, or a simple story to be told, about how the world’s poorest continent might claw its way up to middle-income status. Africa has amazing human talent and brilliant cultural heritages, but its major political centers are, to put it bluntly, falling apart.

https://marginalrevolution.com/marginalrevolution/2021/08/is-africa-losing-its-growth-window.html

MaxRa 16 Aug 2021 15:42 UTC
4 points
in reply to: Hamish Huggard’s comment on: I Ran a Forecasting Tournament at an EA Retreat. Here’s What Happened.
@Simon_Grimm and me ended up also organizing a forecasting tournament. It went really well, people seemed to like it a lot, so thanks for the inspiration and the instructions!

One thing we did differently
- we hanged posters for each question in the main hallway because we thought it would make the forecasts more visible/present and it would be interesting to see what others write down on the poster as their forecast—I would likely do this again, even though hammering all the numbers into an excel sheet was some effort
Questions we used
1. Will the probability of Laschet becoming the next German chancellor be higher than 50% on Hypermind on Sunday, 3pm?
2. Will more than 30 people make a forecast in this tournament?
3. Will one person among the participants do the Giving What We Can pledge during the weekend?
4. During scoring on Sunday before dinner, will two randomly chosen participants report having talked to each other during the weekend? Needs to be more than „Hi“!
5. At the end of Sunday‘s lunch, will there be leftover food in the pots?
6. At Sunday‘s breakfast at 9am, will more than 10 people wear an EA shirt?
7. Will a randomly chosen participant have animal suffering as their current top cause?
8. Will a randomly chosen participant have risks associated with AI as their top cause?
9. At breakfast on Sunday at 9am, will more than half have read at least half of Doing Good Better?
10. Will there be more packages of Queal than Huel at Sunday‘s breakfast?
11. Will there be any rain up until Sunday, 5pm?
12. Will you get into the top 3 forecasters for all other questions except this one?
13. Will participants overall overestimate their probability of getting into the top three?
14. Will more people arrive from the South of Germany than from the North?
15. On average, did people pay more than the standard fee of 100€?

MaxRa 12 Aug 2021 5:55 UTC
3 points
on: Analyzing view metrics on the EA Forum
Cool! Just in case you have the data quickly at hand, I’d‘ve been interested in more than just the top three articles, maybe you could add the top ten? Also, maybe minutes would be the more intuitive unit, compared to something like 2600 seconds.

MaxRa 7 Aug 2021 22:02 UTC
6 points
in reply to: anonymous_ea’s comment on: What EA projects could grow to become megaprojects, eventually spending $100m per year?
I think you’re right. Even if the experts were paid really well for their participation, say 10k per year (maybe as a fixed sum or in expectation given some incentive scheme), and you might have on the order of 50 experts each for 20(?) fields, then you end up with 10 million per year. But probably it wouldn’t even require that, as long as it’s prestigious and is set up well with enough buy-in. Paying for their judgement would make the latter easier I suppose.

MaxRa 7 Aug 2021 18:04 UTC
2 points
in reply to: HStencil’s comment on: What EA projects could grow to become megaprojects, eventually spending $100m per year?
Interesting, the Atlantic article didn’t give this impression. I’d also be pretty surprised if you had to become essentially the cliche of a moderate politician if you’re part of the leadership team of a journalistic organization. In my mind, you’re mostly responsible for setting and living the norms you want the organization to follow, e.g.
- epistemic norms of charitability, clarity, probabilistic forecasts, scout mindset
- values like exploring neglected and important topics with a focus on having an altruistic impact?
And then maybe being involved in hiring the people who have shown promise and fit?