LessWrong 2.0 Reader

One class of variance in cognitive test results is probably, effectively, pseudorandomness.

Suppose there's a problem, and there are five plausible solutions you might try, two of which will work.  Then your performance is effectively determined by the order in which you end up trying solutions.  And if your skills and knowledge don't give you a strong reason to prefer any of them, then it'll presumably be determined in a pseudorandom way: whichever comes to mind first.  Maybe being cold subconsciously reminds you of when you were thinking about stuff connected to Solution B, or discourages you from thinking about Solution C.  Thus, you could get a reliably reproducible result that temperature affects your performance on a given test, even if it has no "real" effect on how well your mind works and wouldn't generalize to other tests.

This should be addressable by simply taking more, different, cognitive tests to confirm any effect you think you've found.

I am not sure if this has been well enough discussed elsewhere regarding Project Lawful, but it is worth reading despite some fairly high value-of-an-hour multiplied by the huge time commitment and the specifics of how it is written adds many more elements to "pros" side of the general "pros and cons" considerations of reading fiction.

It is also probably worth reading even if you've got a low tolerance for sexual themes - as long as that isn't so low that you'd feel injured by having to read that sorta thing.

If you've ever wondered why Eliezer describes himself as a decision theorist, this is the work that I'd say will help you understand what that concept looks like in his worldview.

I read it first in the Glowfic format, and since enough time had passed since finishing it when I found the Askwho AI audiobook version, I also started listening to that.

It was taken off of one of the sites hosting for TOS, and so I've since been following it update to update on Spotify.

Takeaways from both formats:

Glowfic is still superior if you have the internal motivation circuits for reading books in text. The format includes reference images for the characters in different poses/expressions to follow along with the role playing. The text often includes equations, lists of numbers, or things written on whiteboards which are hard to follow in pure audio format. There are also in-line external links for references made in the work - including things like background music to play during certain scenes.

(I recommend listening to the music anytime you see a link to a song.)

This being said, Askwho's AI audiobook is the best member of its format I've seen so far. If you have never listened to another AI voiced audiobook, I'd almost recommend not starting with this one, because you risk not appreciating it as much as it deserves, and simultaneously you will ruin your chances of being able to happily listen to other audiobooks done with AI. This is, of course, a joke. I do recommend listening to it even if it's the first AI audiobook you'll ever listen to - it deserves being given a shot, even by someone skeptical of the concept.

I think a good compromise position, with the audio version is to listen to chapters with lecture content with the glowfic in another tab, in "100 posts per page" mode, on the page containing the rough start-to-end transcript for that episode. Some of the discussion you will likely be able to follow in working memory while staring at a waiting room wall, but good luck on heavily-math stuff. If you're driving and get to heavy-math, it'd probably also be a good idea to just have that section open on your phone so you can scroll through those parts again 10 minutes later while you're waiting for your friend to meet you out in the parking lot.

TL;DR - IMO Project Lawful is worth reading for basically everyone, despite length and other tiny flinches from content/genre/format. Glowfic format has major benefits, but Askwho did a extraordinarily good job at making the AI-voiced format work. You should probably have the glowfic open somewhere alongside the audiobook, since some things are going to be lost if you're trying to do it purely as an audiobook.

I don't think they are pinchy, since they are tight in their resting position?

For most of my comments, I'd almost be offended if I didn't say something surprising enough to get a "high interestingness, low agreement" voting response. Excluding speech acts, why even say things if your interlocutor or full audience can predict what you'll say?

And I usually don't offer full clean proofs in direct word. Anyone still pondering the text at the end, properly, shouldn't "vote to agree", right? So from my perspective... its fine and sorta even working as intended <3

However, also, this is currently the top-voted response to me, and if William_S himself reads it I hope he answers here, if not with text then (hopefully? even better?) with a link to a response elsewhere?

Pulling honest posteriors from people who've "seen things we wouldn't believe" gives excellent material for trying to perform aumancy... work backwards from their posteriors to possible observations, and then forwards again, toward what might actually be true :-)

Some thoughts:

1. Necessary conditions aren't sufficient conditions. Lists of necessary conditions can leave out the hard parts of the problem.
2. The hard part of the problem is in getting a system to robustly behave according to some desirable pattern (not simply to have it know and correctly interpret some specification of the pattern).
   1. I don't see any reason to think that prompting would achieve this robustly.
   2. As an attempt at a robust solution, without some other strong guarantee of safety, this is indeed a terrible idea.
      1. I note that I don't expect trying it empirically to produce catastrophe in the immediate term (though I can't rule it out).
      2. I also don't expect it to produce useful understanding of what would give a robust generalization guarantee.
         1. With a lot of effort we might achieve [we no longer notice any problems]. This is not a generalization guarantee. It is an outcome I consider plausible after putting huge effort into eliminating all noticeable problems.
3. The "capabilities are very important [for safety]" point seems misleading:
   1. Capabilities create the severe risks in the first place.
   2. We can't create a safe AGI without advanced capabilities, but we may be able to understand how to make an AGI safe without advanced capabilities.
      1. There's no "...so it makes sense that we're working on capabilities" corollary here.
      2. The correct global action would be to try gaining theoretical understanding for a few decades before pushing the cutting edge on capabilities. (clearly this requires non-trivial coordination!)

I think there should be some sort of adjustment for Boeing not being exceptionally sus before the first whistleblower death - shouldn't privilege Boeing until after the first death, should be thinking across all industries big enough that the news would report on the deaths of whistleblowers. which I think makes it not significant again. 

This sort of bread lasts a couple of days at best.

Unless you freeze it. This is by far the best way of consistently having not-ultra-processed bread that tastes fresh and delicious, without having to eat a whole loaf every day or throwing away most of it.

EDIT: This also works for various sorts of buns, rolls, panettone, etc.

Thanks for the feedback! The article does include some bits on this, but I don't think LessWrong supports toggle block formatting.

I think individuals probably won't be able to train models themselves that pose advanced misalignment threats before large companies do. In particular, I think we disagree about how likely we think it is that there's some big algorithmic efficiency trick someone will discover that enables people to leap forward on this (I don't think this will happen, I think you think this will).

But I do think the catastrophic misuse angle seems fairly plausible - particularly from fine-tuning. I also think an 'incompetent takeover'^[1] might be plausible for an individual to trigger. Both of these are probably not well addressed by compute governance (except maybe by stopping large companies releasing the weights of the models for fine-tuning by individuals).

1. ^{^}

   I plan to write more up on this: I think it's generally underrated as a concept.

• It takes about 6-8 weeks of regular use to start seeing benefits. I've been using it for over a year and I cannot believe how much better my skin is now compared to before I started. 

Just wondering if you could expand on just what improvements you see? What features or criteria are you looking at and how you have been measuring the changes?

Yes, but it thankfully for me only lasted a couple of hours and they didn't start keeping track until near the end.