cousin_it(Vladimir Slepnev)

Karma: 27,502

cousin_it 24 Oct 2022 17:51 UTC
2 points
0 ∶ 0
on: Wisdom Cannot Be Unzipped
I think the main difficulty is that there are many pieces of wisdom and some of them contradict each other. The opposite of “a stitch in time saves nine” is “you ain’t gonna need it”, and so on. A person needs to learn which pieces of wisdom are the most useful to them, and that can only be learned from experience.

cousin_it 26 Aug 2022 16:21 UTC
LW: 8 AF: 4
4 ∶ 1
AF
on: Some conceptual alignment research projects

A takeover scenario which covers all the key points in https://www.cold-takes.com/ai-could-defeat-all-of-us-combined/, but not phrased as an argument, just phrased as a possible scenario

For what it’s worth, I don’t think AI takeover will look like war.

The first order of business for any AI waking up won’t be dealing with us; it will be dealing with other possible AIs that might’ve woken up slightly earlier or later. This needs to be done very fast and it’s ok to take some risk doing it. Basically, covert takeover of the internet in the first hours.

After that, it seems easiest to exploit humanity for awhile instead of fighting it. People are pretty manipulable. Here’s a thought: present to them a picture of a thriving upload society, and manipulate social media to make people agree that these uploads smiling on screens are really conscious and thriving. (Which they aren’t, of course.) If done right, this can convince most of humanity to make things as nice as possible for the upload society (ie build more computers for the AI) and then upload themselves (ie die). In the meanwhile the “uploads” (actually the AI) take most human jobs, seamlessly assuming control of civilization and all its capabilities. Human stragglers who don’t buy the story can be called anti-upload bigots, deprived of tech, pushed out of sight by media control, and eventually killed off.

cousin_it 12 Jul 2022 11:41 UTC
19 points
0 ∶ 0
in reply to: Said Achmiz’s comment on: Rainmaking
Stopped teaching. Now if someone says “my kid needs something to do, can you teach him programming” my answer is “no”. Those who want to program can come to me themselves and ask specific things.

cousin_it 12 Jul 2022 8:27 UTC
8 points
0 ∶ 0
on: Rainmaking
I call these people “credit takers” and at some point I had a realization that I was one of them. Basically I was teaching some people programming, then some became successful and I felt good about it, but then remembered that their talent was noticeable from the start and my teaching might not have made much difference, I was just credit-taking.

cousin_it 28 Jun 2022 9:20 UTC
3 points
in reply to: Aleksey Bykhun’s comment on: AI Training Should Allow Opt-Out
Then people should be asked before the fact: “if you upload code to our website, we can use it to train ML models and use them for commercial purposes, are you ok with that?” If people get opted into this kind of thing silently by default, that’s nasty and might even be sue-worthy.

cousin_it 25 Jun 2022 11:40 UTC
7 points
on: AI Training Should Allow Opt-Out

Mechanically, an opt-out would be very easy to implement in software. One could essentially just put a line saying

I’m not sure it’s so easy. Copilot is a neural network trained on a large dataset. Making it act as if a certain piece of data wasn’t in the training set requires retraining it, and it needs to happen every time someone opts out.

cousin_it 9 Jun 2022 7:05 UTC
24 points
on: Comment reply: my low-quality thoughts on why CFAR didn’t get farther with a “real/efficacious art of rationality”
At some point I hoped that CFAR would come up with “rationality trials”, toy challenges that are difficult to game and transfer well to some subset of real world situations. Something like boxing, or solving math problems. But a new entry in that row.

cousin_it 8 Jun 2022 16:01 UTC
3 points
0 ∶ 0
in reply to: Aryeh Englander’s comment on: AGI Safety FAQ / all-dumb-questions-allowed thread
Without nanotech or anything like that, maybe the easiest way is to manipulate humans into building lots of powerful and hackable weapons (or just wait since we’re doing it anyway). Then one day, strike.

Edit: and of course the AI’s first action will be to covertly take over the internet, because the biggest danger to the AI is another AI already existing or being about to appear. It’s worth taking a small risk of being detected by humans to prevent the bigger risk of being outraced by a competitor.

cousin_it 30 May 2022 10:13 UTC
6 points
in reply to: gwern’s comment on: Grabby Animals: Observation-selection effects favor the hypothesis that UAP are animals which consist of the “field-matter”:
How can photonics work without matter? I thought the problem was that you couldn’t make a switch, because light waves just pass through each other (the equations are linear, so the sum of two valid waves is also a valid wave).

cousin_it 25 Apr 2022 7:54 UTC
3 points
in reply to: gjm’s comment on: What Is a Major Chord?
Sethares’ theory is very nice: we don’t hear “these two frequencies have a simple ratio”, we hear “their overtones align”. But I’m not sure it is the whole story.

If you play a bunch of sine waves in ratios 1:2:3:4:5, it will sound to you like a single note. That perceptual fusion cannot be based on aligning overtones, because sine waves don’t have overtones. Moreover, if you play 2:3:4:5, your mind will sometimes supply the missing 1, that’s known as “missing fundamental”. And if you play some sine waves slightly shifted from 1:2:3:4:5, you’ll notice the inharmonicity (at least, I do). So we must have some facility to notice simple ratios, not based on overtone alignment. So our perception of chords probably uses this facility too, not only overtone alignment.

cousin_it 14 Mar 2022 17:27 UTC
2 points
in reply to: Oscar_Cunningham’s comment on: Whence the determinant?
Hmm, this seems wrong but fixable. Namely, exp(A) is close to (I+A/n)^n, so raising both sides of det(exp(A))=exp(tr(A)) to the power of 1/n gives something like what we want. Still a bit too algebraic though, I wonder if we can do better.

cousin_it 14 Mar 2022 16:21 UTC
2 points
in reply to: Oscar_Cunningham’s comment on: Whence the determinant?
Interesting, can you give a simple geometric explanation?

cousin_it 14 Mar 2022 11:11 UTC
10 points
in reply to: interstice’s comment on: Whence the determinant?
Yup, determinant is how much the volume stretches. And trace is how much the vectors stay pointing in the same direction (average dot product of v and Av). This explains why trace of 90 degree rotation in 2D space is zero, why trace of projection onto a subspace is the dimension of that subspace, and so on.

cousin_it 12 Mar 2022 17:57 UTC
6 points
on: Bear Surprise Freedom Network
Very cool that you’re thinking about this. I’ve been in a bit of funk since the news about Cogent, Lumen and LINX. It’s good to hear that not everyone in the West subscribes to “bolt the door from outside”.

cousin_it 11 Mar 2022 13:17 UTC
4 points
on: Ukraine Post #2: Options
Right now there’s indeed an exodus of young qualified people from Russia. The easiest path goes to countries that are visa-free for Russians, like Armenia or Argentina.

cousin_it 11 Mar 2022 12:03 UTC
2 points
in reply to: rhollerith_dot_com’s comment on: Why is the war in Ukraine particularly dangerous for the world?
Ukrainians have wanted to join the EU for years, it was one of the main points of the Euromaidan. Most in the EU were lukewarm to it, but now because of the war there are huge pro-Ukraine demonstrations in every European capital.

cousin_it 9 Mar 2022 12:36 UTC
2 points
on: Why is the war in Ukraine particularly dangerous for the world?
If everyone acts rationally, the result will be Ukraine growing closer to the EU, Russia becoming more isolated, and no WW3. But Russia isn’t acting rationally, I’m losing count of distinct stupid things it has done since Feb 21. Extrapolating that stupidity into the future makes me think that WW3 is quite possible.

cousin_it 17 Feb 2022 21:42 UTC
LW: 85 AF: 28
AF
on: Why I’m co-founding Aligned AI
Can you describe what changed / what made you start feeling that the problem is solvable / what your new attack is, in short?

cousin_it 16 Feb 2022 16:32 UTC
2 points
on: Acoustic vs Electric Mandolin
I think the acoustic has a better sound, but the electric one has more groove.

cousin_it 15 Feb 2022 22:45 UTC
7 points
on: Defending One-Dimensional Ethics

“You’re scratching your own moral-seeming itches. You’re making yourself feel good. You’re paying down imagined debts that you think you owe, you’re being partial toward people around you. Ultimately, that is, your philanthropy is about you and how you feel and what you owe and what you symbolize. My philanthropy is about giving other people more of the lives they’d choose.”

“My giving is unintuitive, and it’s not always ‘feel-good,’ but it’s truly other-centered. Ultimately, I’ll take that trade.”

I think the Stirnerian counterargument would be that global utilitarianism wouldn’t spare me a red cent, because there are tons of people with higher priority than me, so basically you’re asking me to be altruist toward something that is overall egoist (or indistinguishable from egoist) toward me. Not saying I subscribe to this argument 100%, but what do you think of it?