2019 AI Alignment Literature Review and Charity Comparison 2019-12-19T03:00:54.708Z · score: 130 (34 votes)
2018 AI Alignment Literature Review and Charity Comparison 2018-12-18T04:46:55.445Z · score: 195 (63 votes)
2017 AI Safety Literature Review and Charity Comparison 2017-12-24T18:52:31.816Z · score: 76 (27 votes)
2018 AI Safety Literature Review and Charity Comparison 2017-12-20T22:04:47.174Z · score: 2 (2 votes)
2016 AI Risk Literature Review and Charity Comparison 2016-12-15T00:19:21.966Z · score: 7 (8 votes)
Contrarian LW views and their economic implications 2014-10-08T23:48:04.250Z · score: 22 (20 votes)
Confirmation Bias Presentation 2014-06-05T21:07:31.918Z · score: 2 (3 votes)
Meetup : Princeton NJ Meetup 2014-03-23T00:22:06.409Z · score: 1 (2 votes)
Meetup : Princeton NJ Meetup 2014-02-02T22:32:10.247Z · score: 0 (1 votes)
Meetup : Princeton NJ Meetup 2013-10-22T02:10:25.174Z · score: 2 (3 votes)
Giving What We Can September Internship 2013-02-18T20:03:56.667Z · score: 4 (7 votes)
[minor] Separate Upvotes and Downvotes Implimented 2013-01-29T10:31:21.726Z · score: 29 (30 votes)
[Link]: 80,000 hours blog 2012-02-26T14:34:58.457Z · score: 20 (23 votes)
Counterfactual Coalitions 2012-02-16T21:42:52.639Z · score: 23 (23 votes)
Best Intro to LW article for transhumanists 2011-10-28T02:30:35.471Z · score: 6 (7 votes)
In Defense of Objective Bayesianism: MaxEnt Puzzle. 2011-01-06T00:56:50.739Z · score: 6 (7 votes)
Link: Facing the Mind-Killer 2010-12-18T00:57:08.114Z · score: 8 (15 votes)
Oxford (UK) Rationality & AI Risks Discussion Group 2010-11-02T19:10:30.494Z · score: 2 (5 votes)
A Player of Games 2010-09-23T22:52:38.849Z · score: 15 (24 votes)
Burning Man Meetup: Bayes Camp 2010-08-25T06:14:54.005Z · score: 16 (19 votes)


Comment by larks on Covid-19 6/4: The Eye of the Storm · 2020-06-05T02:27:05.227Z · score: 7 (4 votes) · LW · GW

I attempted to produce a rough estimate of this here (excerpted below):

... One (BERI funded!) study suggested that banning large gatherings reduced r0 by around 28%.
Unfortunately, protests seem in many ways ideal for spreading the disease. They involve a large number of people in a relatively small area for an extended period of time. Even protests which were advertised as being socially distanced often do not end up that way. While many people wear masks, photos of protests make clear that many do not, and those that are are often using cloth masks that are significantly less effective than surgical or n95s in the face of repeated exposure. Additionally, protests often involve people shouting or chanting, which cause infectious droplets to be released from people's mouths. Exposure to tear gas can apparently also increase susceptibility, as well as cramped indoor conditions for those arrested.
It's hard to estimate how many new cases will be caused by the protests, because there doesn’t seem to be good statistics on the number of people at protests, so we can't model the physical dynamics easily. A simple method would be to assume we have lost the benefits of the ban on large gatherings over the last week or so. On the one hand, this may be an over-estimate, because fortunately most people continue to socially distance, and protests take place mainly outside. On the other hand, protesters are actively seeking out (encouraging others to seek out) boisterous large gatherings in a way they were not pre-March, which could make things even worse. On net I suspect it may under-estimate the incremental spread, but given the paucity of other statistics we will use it as our central scenario.
If the r0 was around 0.9 before, this suggests the protests might have temporarily increased it to around 1.25, and hopefully it will quickly return to 0.9 after the protests end. Even if we assume no chain infections during the protest - so no-one who has been infected at a protest goes on to infect another protester - this means the next step in disease prevalence would be a 25% increase instead of a 10% decrease. Unfortunately the exponential nature of infection means this will have a large impact. If you assume around 1% of the US was infected previously, had we stayed on the previous r0=0.9 we would end up with around 9% more of the population infected from here on before the disease was fully suppressed. In contrast, with this one-time step-up in r0, we will see around 12.5% of the population infected from here - an additional 3.5% of the population.
Assuming an IFR of around 0.66%, that's a change from around 190,000 deaths to more like 265,000. Protesters skew younger than average, suggesting that this IFR may be an over-estimate, but on the other hand, they are also disproportionately African American, who seem to be more susceptible to the disease, and the people they go on to infect will include older people.
Comment by larks on 2018 AI Alignment Literature Review and Charity Comparison · 2019-12-19T03:02:37.941Z · score: 5 (2 votes) · LW · GW

See next year's post here.

Comment by larks on Free Money at PredictIt? · 2019-09-26T22:42:43.311Z · score: 2 (1 votes) · LW · GW

I still found this helpful as it allowed me to exit my directional Yang and Buttigieg positions with negative transaction cost.

Comment by larks on Honoring Petrov Day on LessWrong, in 2019 · 2019-09-26T22:10:21.171Z · score: 24 (7 votes) · LW · GW

I would like to add that I think this is bad (and have the codes). We are trying to build social norms around not destroying the world; you are blithely defecting against that.

Comment by larks on Power Buys You Distance From The Crime · 2019-08-03T16:19:46.446Z · score: 14 (4 votes) · LW · GW
This case is more complicated than the corporate cases because the powerful person (me) was getting merely the appearance of what she wanted (a genuine relationship with a compatible person), not the real thing. And because the exploited party was either me or Connor, not a third party like bank customers. No one thinks the Wells Fargo CEO was a victim the way I arguably was.

I think you have misunderstood the Wells Fargo case. These fake accounts generally didn't bring in any material revenue; they were just about internal 'number of new accounts targets'. It was directly a case of bank employees being incentivised to defraud management and investors, which they then did. If ordinary Wells employees had not behaved fraudulently, all the targets would have been missed, informing management/investors about their mis-calibration, and more appropriate targets would have been set. In this case power didn't buy distance from the crime, but only in the sense that it meant you couldn't tell you were being cheated.

For more on this I recommend the prolific Matt Levine:

There's a standard story in most bank scandals, in which small groups of highly paid traders gleefully and ungrammatically conspire to rip-off customers and make a lot of money for themselves and their bank. This isn't that. This looks more like a vast uprising of low-paid and ill-treated Wells Fargo employees against their bosses.
So that's about 2.1 million fake deposit and credit-card accounts, of which about 100,000 -- fewer than 5 percent -- brought in any fee income to Wells Fargo. The total fee income was $2.4 million, or about $1.14 per fake account. And that overstates the profitability: Wells Fargo also enrolled people for debit cards and online banking, but the CFPB doesn't bother to count those incidents, or suggest that any of them led to any fees. Which makes sense: You'd expect online banking and debit cards to be free, if you never use them or even know about them. Meanwhile, all this dumb stuff seems to have occupied huge amounts of employee time that could have been spent on more productive activities. If you divide the $2.4 million among the 5,300 employees fired for setting up fake accounts, you get about $450 per employee. Presumably it cost Wells Fargo way more than that just to replace them.
In the abstract, you can see why Wells Fargo would emphasize cross-selling of multiple "solutions" to customers. It is a good sales practice; it both indicates and encourages customer loyalty. If your customers have a checking account, and a savings account, and a credit card and online banking, all in one place, then they'll probably use each of those products more than if they had only one. And when they want a new, lucrative product -- a mortgage, say, or investment advice -- they're more likely to turn to the bank where they keep the rest of their financial life. 
But obviously no one in senior management wanted this. Signing customers up for online banking without telling them about it doesn't help Wells Fargo at all. No one feels extra loyalty because they have a banking product that they don't use or know about. Even signing them up for a credit card without telling them about it generally doesn't help Wells Fargo, because people don't use credit cards that they don't know about. Cards with an annual fee are a different story -- at least you can charge them the fee! -- but it seems like customers weren't signed up for many of those.  This isn't a case of management pushing for something profitable and getting what they asked for, albeit in a regrettable and illegal way. This is a case of management pushing for something profitable but difficult, and the workers pushing back with something worthless but easy.

Comment by larks on Financial engineering for funding drug research · 2019-05-17T03:04:28.949Z · score: 5 (3 votes) · LW · GW

Is this very different from founding a pharmaceutical company?

Comment by larks on Strategic implications of AIs' ability to coordinate at low cost, for example by merging · 2019-05-02T20:51:24.945Z · score: 10 (2 votes) · LW · GW

Critch wrote a related paper:

Existing multi-objective reinforcement learning (MORL) algorithms do not account for objectives that arise from players with differing beliefs.Concretely, consider two players with different beliefs and utility functions who may cooperate to build a machine that takes actions on their behalf. A representation is needed for how much the machine’s policy will prioritize each player’s interests over time. Assuming the players have reached common knowledge of their situation, this paper derives a recursion that any Pareto optimal policy must satisfy. Two qualitative observations can be made from the recursion: the machine must (1) use each player’s own beliefs in evaluating how well an action will serve that player’s utility function, and (2) shift the relative priority it assigns to each player’s expected utilities over time, by a factor proportional to how well that player’s beliefs predict the machine’s inputs. Observation (2) represents a substantial divergence from naive linear utility aggregation (as in Harsanyi’s utilitarian theorem, and existing MORL algorithms), which is shown here to be inadequate for Pareto optimal sequential decision-making on behalf of players with different beliefs.

Toward negotiable reinforcement learning: shifting priorities in Pareto optimal sequential decision-making

Comment by larks on Strategic implications of AIs' ability to coordinate at low cost, for example by merging · 2019-05-02T20:44:47.325Z · score: 2 (1 votes) · LW · GW

War only happens if two agents don’t have common knowledge about who would win (otherwise they’d agree to skip the costs of war).

They might also have poorly aligned incentives, like a war between two countries that allows both governments to gain power and prestige, at the cost of destruction that is borne by the ordinary people of both countries. But this sort of principle-agent problem also seems like something AIs should be better at dealing with.

Comment by larks on Literature Review: Distributed Teams · 2019-04-16T16:06:48.856Z · score: 12 (6 votes) · LW · GW

In light of this:

Build over-communication into the process.
In particular, don’t let silence carry information. Silence can be interpreted a million different ways (Cramton 2001).

Thanks for writing this! I found it very interesting, and I like the style. I particularly hadn't properly appreciated how semi-distributed was worth than either extreme. It's disappointing to hear, but seemingly obvious in retrospect and good to know.

Comment by larks on 2018 AI Alignment Literature Review and Charity Comparison · 2019-01-05T18:45:23.520Z · score: 2 (1 votes) · LW · GW

Thanks for sharing, seems like a reasonable take to me.

Comment by larks on 2018 AI Alignment Literature Review and Charity Comparison · 2019-01-05T18:43:10.417Z · score: 2 (1 votes) · LW · GW

I definitely being near AI hubs is helpful, and I'd be interested in supporting any credible new groups that started in other hubs.

Thanks for that extra info on CHAI staff. In general my objections to the bay area are partly about the EA/LW culture there, and partly about the broader culture. I did end up donating to CHAI despite this!

Comment by larks on 2018 AI Alignment Literature Review and Charity Comparison · 2019-01-05T18:22:33.116Z · score: 4 (2 votes) · LW · GW

Thanks! I have fixed most of the typos.

Comment by larks on In Defense of Finance · 2018-12-19T00:37:01.560Z · score: 3 (2 votes) · LW · GW

Especially as in recent years investor preferences for lower risk, low beta, low vol, higher yield stocks (like utilities and staples) has been well documented as strong.

One related fact is that (at least some of the banks) feel like they haven't gotten credit for the risk reductions they have done. Given their lower leverage now, they feel like they should have higher multiples, whereas actually their relative multiples have compressed vs the market vs pre-crisis. Of course, this may be because their risk was under-estimated pre-crisis, so their relative multiple was too high.

Comment by larks on In Defense of Finance · 2018-12-19T00:33:25.226Z · score: 18 (6 votes) · LW · GW

At least in public equity markets the size premium is very weak. My team looked at it and decided not to use it as a factor to guide our investing. It's closely correlated to an illiquidity premia, which I do believe in.

Comment by larks on Get genotyped for free ( If your IQ is high enough) · 2018-12-15T19:04:15.139Z · score: 2 (1 votes) · LW · GW

Update: Jeff says they only ever sent him part of his data.

Comment by larks on The Vulnerable World Hypothesis (by Bostrom) · 2018-11-17T14:48:14.663Z · score: 4 (2 votes) · LW · GW

Nick's space papers are largely about how to harvest large amounts of utility from the galaxy, not about how to increase humanity's robustness. And yes, there are some Xrisks (including the one I am focused on) that space colonies do not help with, but the reader may not be convinced of these, so it is surely worth mentioning that some risks would be guarded against with interstellar diversification. If nothing else you should probably argue that space colonization is not an adequate solution for these reasons.

Comment by larks on Some cruxes on impactful alternatives to AI policy work · 2018-11-17T03:02:37.769Z · score: 30 (12 votes) · LW · GW
A study by the investment-research firm Strategas which was cited in The Economist and the Washington Post compared the 50 firms that spent the most on lobbying relative to their assets, and compared their financial performance against that of the S&P 500 in the stock market; the study concluded that spending on lobbying was a "spectacular investment" yielding "blistering" returns comparable to a high-flying hedge fund, even despite the financial downturn of the past few years.

I think I read this research while I was a Strategas client; if I'm remembering it correctly it was extremely poorly done. Short back test (just a few years), garden of forking paths, etc. Most sell-side research is not epistemically rigourous and Strategas is not one of the better firms. I would not put much weight on this research.

There is widespread agreement that a key ingredient in effective lobbying is money. This view is shared by players in the lobbying industry.

Well of course lobbyists would say they're worth the money!

Comment by larks on Values determined by "stopping" properties · 2018-03-22T23:33:37.355Z · score: 9 (3 votes) · LW · GW
This, by the way, explains my intuitive dislike for some types of moral realism. If there are true objective moral facts that humans can access, then whatever process counts as "accessing them" becomes... a local stopping condition for defining value.

I'm not sure I understand what you're getting at here. Yes, they are both local stopping conditions, but there seems to be a clear dis-analogy. The other local stopping conditions seem to be bad not because they are stopping conditions, but because most contemporary people don't want to end up as Lotus-Eaters, or as mindless outsourcers. We would oppose such a development even if it wasn't stable! For example, a future where we oscillate between lotus-eaters and mindless outsourcers seems about as bad as either individual scenario. So it's not really the stability we object to.

But in that case, it's not clear why we should be opposed to the moral realism. After all, many people would like to go there, even if we are presently a long way away.

Comment by larks on Open Thread, February 1-14, 2012 · 2018-03-06T04:01:16.507Z · score: 0 (0 votes) · LW · GW

the one academic doing good work in the area is Sheffer, who is running a longitudinal survey which may or may not have enough statistical power to rule out particularly dramatic variances in outcomes. (Sheffer mentions the selection bias problem but seems to have the attitude that it's not a problem for her work.)

Was there any follow-up here?

Comment by larks on Experiences in applying "The Biodeterminist's Guide to Parenting" · 2018-01-08T02:13:07.247Z · score: 0 (0 votes) · LW · GW

The bioterminist's guide is now 5 years old. Does anyone know of an updated version?

Comment by larks on 2017 AI Safety Literature Review and Charity Comparison · 2017-12-30T20:21:35.693Z · score: 8 (2 votes) · LW · GW

Thanks, I'm honoured! I've sent you a private message.

Comment by larks on More Dakka · 2017-12-09T16:43:28.394Z · score: 6 (4 votes) · LW · GW

In our house we started a tradition of holding hands and taking turns saying something we're grateful before dinner each night. We then soft-evangalise this by having guests over and including them - most notably to hundreds of people at our wedding.

Comment by larks on Inadequacy and Modesty · 2017-11-01T02:00:03.086Z · score: 3 (1 votes) · LW · GW

Yup, just logged back in to make that guess. Would also explain the Japan commentary.

Comment by larks on Inadequacy and Modesty · 2017-10-29T23:58:10.382Z · score: 9 (3 votes) · LW · GW

Great article, and I'm glad to see you've returned to Less(er)wrong.

One very very small question: speaking as one of the hedge fund guys you mention who happened to be long MSFT into a very successful quater on friday, why did your Microsoft example use a share price of $37.70? We're at $83.81 now!

Comment by larks on Multidimensional signaling · 2017-10-17T00:08:55.941Z · score: 3 (2 votes) · LW · GW

Presumably it would also lead us to think that having lots of free time, or being very concerned about [clothes/wit/grades] was better - but this does not seem to be obveously the case.

Comment by larks on Beta - First Impressions · 2017-10-14T03:32:24.726Z · score: 1 (1 votes) · LW · GW

First of all, thanks for making this all! :)

One suggestiong: coudl we hvae a sepll-ckecher for the cmmonent box?

Comment by larks on There's No Fire Alarm for Artificial General Intelligence · 2017-10-14T03:21:35.921Z · score: 32 (18 votes) · LW · GW

Occationally we run surveys of ML people. Would it be worth asking them what their personal fire alarm would be, or what they are confident will not be achieved in the next N years? This would force them to make a mental stance that might help them achieve some cognitive dissonance later, and also allow us to potentially follow up with them.

Comment by larks on June 2017 Media Thread · 2017-06-03T22:11:15.683Z · score: 0 (0 votes) · LW · GW

Why is there no way to downvote, report or otherwise punish this comment?

Comment by Larks on [deleted post] 2017-06-02T02:03:03.335Z

I think Plato fans would probably argue I'm being somewhat unfair. If nothing else, the society described was intended as a metaphor for the virtuous person, not necessarily as an actually good society in itself.

More relevantly, I didn't intend for this to be a major criticism of your endeavor. I think if you can avoid sexual conflict (for which I recommend celibacy on your part) this could be worthwhile for (some) people.

Comment by Larks on [deleted post] 2017-06-01T03:07:24.362Z

The section on goals reminded me a little of Plato's Republic. The perfect society involves sacrificing all wealth, art, free expression, and what does it offer in return?

Victory in war against similar-sized enemies.

Comment by Larks on [deleted post] 2017-05-28T21:46:11.295Z

One idea that is probably necessary but not sufficient is for the Commander (and anyone else with any authority in the house) to have an absolute commitment not to sleep with anyone else in the house.

Edit: with this rule, a different/earlier version of me might have been interested. Without it I would never be.

Comment by larks on Thoughts on civilization collapse · 2017-05-07T18:51:11.552Z · score: 3 (3 votes) · LW · GW

Cities, with their large and varied-skill workforce, will suffer less than the countryside.

Cities have a large and varied workforce, but many of their skills lie in things that rely on civilisation remaining intact. Tax lawyers, bartenders, yoga instructors, investment bankers etc. all seem like they would be more of a liability than an asset in such a scenario. Whereas the countryside has skills more focused around food production, and a lower population density reduces the risks of food riots.

Comment by larks on survey about biases in the investment context · 2017-03-25T18:16:18.753Z · score: 0 (0 votes) · LW · GW

One of the pages crashed on me. When I refreshed the page I got the next question (5) I think, and this error message.

Comment by larks on 80,000 Hours: EA and Highly Political Causes · 2017-01-27T02:59:55.919Z · score: 5 (5 votes) · LW · GW

You should post this on the EA forum

Comment by larks on CFAR’s new focus, and AI Safety · 2016-12-03T04:12:03.324Z · score: 11 (11 votes) · LW · GW

headline: CFAR considering colonizing Antarctica.

Comment by larks on Google Deepmind and FHI collaborate to present research at UAI 2016 · 2016-11-23T02:14:37.633Z · score: 1 (1 votes) · LW · GW

Hey Stuart,

It seems like much of the press around this paper discussed it as a 'big red button' to turn off a rogue AI. This would be somewhat in-line with your previous work around limited impact AIs who are indifferent to their being turned off, but it doesn't seem to really describe this paper. My interpretation of this paper is it doesn't make the AI indifferent to interruption, or prevent the AI from learning about the button - it just helps the AI avoid a particular kind of distraction during the training phase. Being able to implement the interruption is a separate issue - but it seems that designing a form of interruption that the AI won't try to avoid is the tough problem. Is this reading right, or am I missing something?

Comment by larks on Google Deepmind and FHI collaborate to present research at UAI 2016 · 2016-07-12T00:18:07.817Z · score: 0 (0 votes) · LW · GW

Yup, I think I understand that, and agree you need to at least tend to one. I'm just wondering why you initially use the loser definition of theta (where it doesn't need to tend to one, and can instead be just 0 )

Comment by larks on Google Deepmind and FHI collaborate to present research at UAI 2016 · 2016-07-10T03:33:57.592Z · score: 0 (0 votes) · LW · GW

Very interesting paper, congratulations on the collaboration.

I have a question about theta. When you initially introduce it, theta lies in [0,1]. But it seems that if you choose theta = (0n)n, just a sequence of 0s, all policies are interruptible. Is there much reason to initially allow such a wide ranging theta - why not restrict them to converge to 1 from the very beginning? (Or have I just totally missed the point?)

Comment by larks on [Link] Mutual fund fees · 2016-04-29T01:35:52.369Z · score: 0 (0 votes) · LW · GW

Yes, I agree it's possible to do them correctly. But few people do, and finding positive results is so much more likely if you do them wrong that poor methodology should be the default explanation for any such positive result.

Comment by larks on [Link] Mutual fund fees · 2016-04-27T23:42:37.943Z · score: 1 (1 votes) · LW · GW

They don't mention being survivorship-bias free, which I would expect them to if they were.

Comment by larks on [Link] Mutual fund fees · 2016-04-27T00:47:58.885Z · score: 1 (1 votes) · LW · GW

I think this is very likely. When going to label funds, naturally currently existing ones come to mind - but these are the survivors. Failed activists funds don't leave much of a track record.

Comment by larks on Open Thread April 11 - April 17, 2016 · 2016-04-13T23:48:19.552Z · score: 3 (3 votes) · LW · GW

Did it work? While I would give him full credit, I can easily imagine many teachers not approving.

Comment by larks on AlphaGo versus Lee Sedol · 2016-03-10T03:10:01.386Z · score: 1 (1 votes) · LW · GW

What do you mean by "one handshake"?

Comment by larks on What is the future of nootropic drugs? Why can't there be ones more effective than ones that have existed for 15+ years? · 2016-03-07T03:06:39.214Z · score: 0 (0 votes) · LW · GW

The FDA will not give you a patent

The issue isn't patents (which are not awarded by the FDA anyway) but whether they will give your drug approval to market.

Comment by larks on Open thread, Oct. 26 - Nov. 01, 2015 · 2015-10-27T00:06:30.149Z · score: 5 (5 votes) · LW · GW

Has anyone been to the Young Cryonicists Gathering? Is it worth going to? Anyone planning on attending the one in California in April?

Previous coverage on LW: positive and negative.

Comment by larks on Median utility rather than mean? · 2015-09-09T01:11:31.310Z · score: 0 (0 votes) · LW · GW

In finance we use medians a lot more than means.

Comment by larks on Experiences in applying "The Biodeterminist's Guide to Parenting" · 2015-09-05T21:16:42.193Z · score: 0 (0 votes) · LW · GW

I'm looking to buy a sofa without flame retardants. The Center for Enviromental Health suggests that all IKEA products are fine, but at least in 2012 it seems that they instead substituted another chemical flame retardant, TRIS. Does anyone know if IKEA furniture is now chemical flame retardant free, or if there are any other good options for below $1,000 ?

Comment by larks on Stupid Questions September 2015 · 2015-09-05T21:09:12.954Z · score: 1 (1 votes) · LW · GW

US firms? Your main China exposure is going to come from your Aussie mining exposure.

Comment by larks on A list of apps that are useful to me. (And other phone details) · 2015-08-22T16:40:15.764Z · score: 1 (1 votes) · LW · GW

I just installed 6 apps.

  • CPU Thermometer
  • PowerCalc
  • Advanaced Signal Status
  • Compass
  • First Aid (US Red Cross)
  • Heart Rate

Thanks for writing this.

Comment by larks on Yvain's most important articles · 2015-08-16T14:25:57.194Z · score: 12 (14 votes) · LW · GW

I thought the biodeterminists guide was one of the most useful things I've ever read. I'd love it if Yvain would write the same for longevity, general fitness, IQ, etc.