RamblinDash

Karma: 324

RamblinDash 19 Sep 2023 16:22 UTC
1 point
−5
in reply to: Daniel Kokotajlo’s comment on: The Talk: a brief explanation of sexual dimorphism
Arguably you do in fact see this, at least as to 3-type species. Many bees, ants and other eusocial insects have queens, drones, and workers. Workers are often described as sterile females, but it seems like that’s us 2-typers imposing a 2-type frame on what are clearly 3 types.

RamblinDash 8 Sep 2023 13:44 UTC
13 points
10
in reply to: dr_s’s comment on: Bring back the Colosseums
If you reintroduced the Coliseum, it’d be people desperate for money and the occasional guy with the actual agency to live out his dream fighting in it, and the aforementioned vast crowd of whiners with no self-awareness would be watching it on TV all the same, while ranting about how incompetent those gladiators are, and that they’d be much better, if only not for [insert convenient excuse here].
Indeed, the NFL exists, and you have described it to a tee. Given the amount and severity of injuries, I would say it’s a very close substitute.

RamblinDash 8 Sep 2023 13:22 UTC
6 points
0
on: Explained Simply: Quantilizers
In my other aligning-a-human-level-intelligence project (parenting), my kids get “points” for trying new foods. We are often having arguments about what kinds of trivial modifications to an old food will make it count as a new food. This seems like it could have a similar problem—couldn’t a superintelligence generate thousands of non-substantive variations for an effective, dangerous action while electing not to do so for other actions?
Similarly, since the tails come apart, perhaps it would be better to sample from 85-95%ile actions instead of sampling from 90-100%ile actions.

RamblinDash 27 Aug 2023 17:08 UTC
3 points
0
on: Will issues are quite nearly skill issues
Another way to operationalize this difference you called out at the end is by saying, counterfactually if I were sufficiently motivated to do X, I would do it. Of course this leads you just as dense a philosophical thicket, just moving it to the nature of counterfactuals rather than the nature of will.

But in some ways your conception of the problem is also too narrow because it seems to partly include a distinction between muscle skills and cognitive skills? I am not “able” to beat Magnus Carlson at chess but it isn’t because I’m physically unable to move the pieces appropriately.

RamblinDash 31 Jul 2023 18:22 UTC
2 points
0
in reply to: astridain’s comment on: Lack of Social Grace Is an Epistemic Virtue
And rationalists might still say “why are we spending all this brainpower encrypting our conversations just so that the other guy can decrypt them again? it’s unnecessary at best”.
We do this so that the ugly guy can get the message without creating Common Knowledge of his ugliness.

RamblinDash 6 Jul 2023 15:32 UTC
1 point
0
in reply to: A.H.’s comment on: Optimized for Something other than Winning or: How Cricket Resists Moloch and Goodhart’s Law
It may be that there isn’t big enough money in cricket for it to be attractive to hypercompetitive athletes and coaches who are most likely to apply that optimization pressure?

RamblinDash 5 Jul 2023 13:15 UTC
16 points
4
on: Optimized for Something other than Winning or: How Cricket Resists Moloch and Goodhart’s Law
In real (American gridiron) football, this problem is solved by the NFL tweaking the rules every year. They understand they are producing an entertainment product, and a typical pattern is something like this:
1. The New England Patriots come up with some clever rules exploit that ekes out an advantage, and maybe wins them a game.
2. Everyone goes “can they really do that??” and whines that it’s very unfair, even though it’s within the rules.[1]
3. If its early in the season, sometimes other teams begin to do the thing.
4. Between seasons, the NFL decides that this play pattern makes for worse TV, and changes the rules to eliminate it.
5. (Goto step 1)
As a fan of both the New England Patriots and David Sirlin, I find this cycle itself very entertaining. I am glad when the Patriots do this because it helps them win and it is, IMO, in the true spirit of competition to make all legal moves in service of victory.
[1] I recognize that the Patriots are widely believed to have cheated on several occasions. I don’t condone cheating, and don’t think that cheating makes one a “lovable scamp” or whatever. I personally find the actual evidence that the Patriots cheated on some of those occasions to be less than credible (and people’s views on it colored by their negative reaction to the Patriots Cycle), but I also recognize that I am biased and likely not able to fairly evaluate that evidence.

RamblinDash 7 Jun 2023 18:43 UTC
4 points
3
in reply to: lc’s comment on: Intelligence Officials Say U.S. Has Retrieved Craft of Non-Human Origin
Yeah, I really strongly agree with this. If high-tech aliens have been in contact with Earth for some significant time, the general public weren’t aware, and we aren’t all dead? “Halt and Catch Fire” moment for sure (wanted to make that a link to where I learned that phrase in The Sequences but I couldn’t find it by search. Did I confabulate??)

RamblinDash 20 May 2023 11:52 UTC
7 points
4
in reply to: Richard_Ngo’s comment on: Buying Tall-Poppy-Cutting Offsets
I had this thought too but there’s kind of a problem, which is that the more compelling the example of “tall poppy”, the more politically controversial which can distract from and undermine your message. I kinda think Elon Musk is the perfect example to use though. I wish the post could somehow autodetect the reader’s politics and select statements about Elon accordingly.

“Elon Musk [lately seems to be going off the antisemitism deep end/does a lot of securities fraud/comes up with dumb fake ideas like Hyperloop/calls people pedos for no reason/exaggerates how good Tesla autopilot is in a way that seems likely to kill people] but I still really appreciate how he [jump-started the modern electric car industry/brought innovation back to space launches/something something Starlink].

RamblinDash 2 May 2023 13:41 UTC
9 points
7
on: The Moral Copernican Principle
I have seen this idea presented as Natural Law Theory. The dumb unsophisticated version of Natural Law theory purport that certain laws are universal due to being derived from some kind of abstract first principles. The smart versions of Natural Law Theory posit that these “natural laws” are more like laws of engineering than like laws of physics—if you want a bridge that will stand up, you need to follow these kinds of rules. If you want a human society that will “stand up”, you need to follow these kinds of rules. But the nature of those rules are derived from facts about humans, not from abstract universal principles or formal logic.

RamblinDash 2 May 2023 1:08 UTC
9 points
0
on: The Apprentice Thread 2
[MENTOR]
This is a bit off-center from the normal LW topic of trying to prevent AI Doom, but I’m interested in helping out people who are interested in law or public policy. I don’t post here much (long time near-lurker), but I am a state government lawyer who works in public health and consumer finance. I am interested in:
- Helping people decide the age-old question “should I go to law school?”
- Helping young law students, lawyers, or policy-curious folks figure out how to get started in the field and/or where would be impactful for them to work
- Help people understand how workaday state government enforcement operates on the ground
- Helping lawyers or nonlawyers with their expository/persuasive writing (a lawyer is primarily a professional reader and writer, but don’t ask me to help with creative/fiction writing lol)
Will provide my real name and links to public facing things I’ve done on request. I don’t have any particular need or use for an “Apprentice” per se, so I see what I’m offering as a mentor/mentee model more than a master/apprentice model.

RamblinDash 27 Apr 2023 17:08 UTC
7 points
3
in reply to: gjm’s comment on: Transcript and Brief Response to Twitter Conversation between Yann LeCunn and Eliezer Yudkowsky
On the third hand, the Luddites made a prediction about a bad (for them) outcome, and were absolutely correct. They were against automatic looms because they thought the autolooms would replace their artisan product with lower quality goods and also worsen their wages and working conditions. They were right: https://www.smithsonianmag.com/history/what-the-luddites-really-fought-against-264412/

RamblinDash 28 Mar 2023 13:54 UTC
2 points
0
in reply to: cubefox’s comment on: The salt in pasta water fallacy
Right, but if you wait for the water to boil before you put the pasta in, then you are waiting a little longer before adding the pasta. Then cooking the pasta slightly shorter after you put it in.

RamblinDash 28 Mar 2023 11:57 UTC
1 point
1
in reply to: tailcalled’s comment on: Don’t take bad options away from people
Admittedly I have not. TBH I’m not sure i could tell even if I did. But I’m very confident just by looking at the world around me that predictions by minwage opponents of imminent mass unemployment every time it’s raised are wrong.

What I also know is that the ultimate effect is controversial among respected economists. What I deduce from this is that if there’s an effect it must be small, because if it was big it would be obvious.

RamblinDash 28 Mar 2023 11:50 UTC
3 points
in reply to: DirectedEvolution’s comment on: The Epsilon Fallacy
Right but i think part of the argument being made above is that we shouldn’t bother will all this pie-in-the-sky stuff because the gas transition has caused almost all the actual emission reduction. It’s boneheaded as a statement on climate policy, but in a way i think is constructive to explore and apply more broadly.

If you have achieved big gains doing some thing X, but you are very confident that ultimately X has fundamental limitations such that it can’t possibly solve your ultimate problem....then it’s not good to put all your resources into X. (cf RLHF, i guess)

RamblinDash 27 Mar 2023 18:03 UTC
3 points
in reply to: DirectedEvolution’s comment on: The Epsilon Fallacy
The other problem with the Natural Gas argument is right there in the premise. If burning natural gas is twice as carbon efficient as burning coal (X emissions → X/2 emissions), you can never do better than halving your emissions by switching everything to natural gas. So even though it’s good that gas has led to lower emissions so far, we must necessarily work on these other technologies if we ever want to do better than X/2.

RamblinDash 27 Mar 2023 17:56 UTC
10 points
1
on: The salt in pasta water fallacy
Also you would have to add back in additional time to get the water to its (new, higher) boiling point in the first place...

RamblinDash 27 Mar 2023 13:37 UTC
8 points
1
in reply to: Dumbledore's Army’s comment on: Don’t take bad options away from people
The canonical example of this is minimum wage laws. There is a lot of economic theory about how (reasonable-level) minimum wages create unemployment. And many people continue to insist that this is in fact the case, based on pretty solid supply/demand reasoning.
But in most circumstances, big empirical studies persistently fail to show any evidence that the predicted unemployment actually occurs. Why? I can tell some just-so stories about it, but the real answer I think is “geez, I don’t know, real life is much more complex than simple supply/demand models.”

RamblinDash 15 Mar 2023 14:38 UTC
3 points
0
in reply to: Ninety-Three’s comment on: Parasitic Language Games: maintaining ambiguity to hide conflict while burning the commons
Although to the extent that the founder’s savvy is used for the purpose of taking the company public even though their product is not as good as they “pre-truthed” it, then the ultimate purpose is that the founder and the early investors are essentially colluding to defraud less-savvy IPO investors. Seems not great.
SQZ Biotech is possibly a good example of this (I live nearby so have followed the story but don’t have any inside info about this company).

RamblinDash 13 Mar 2023 15:21 UTC
1 point
0
in reply to: Ninety-Three’s comment on: Parasitic Language Games: maintaining ambiguity to hide conflict while burning the commons
This still creates another problem for founders who aren’t part of the good-ol-boys network and don’t know they are supposed to “pre-truth.” Their companies will be evaluated worse than they “should” by VCs because VCs downgrade their actually currently true claims as if they were pre-truths. Nobody is being “deceived” per se, but these founders are being harmed.