LessWrong 2.0 Reader

Are there types of published alignment research that you think were (more likely to be) good to publish? If so, I'd be curious to see a list.

I like this a lot. You are programming for the human brain now.

It also seems nice that can implement each step in this program in executable code, and then you don't need to perform that step manually. You might even write little helper programs to perform the tasks, which can then later be used if you decide to automate the script more.

It also seems useful for developing an algorithm. Often I might want to understand what my brain is doing and have an algorithm that emulates what my brain is doing.

Maybe this method can be used to write down a very high-level description of the steps that I think my brain is doing and then see whether me now following that procedure blindly leads to the correct result. If you get the correct result, you can then try to fill in more details, automating each individual step a bit more, and then checking if you still get the same result, and so on.

Left the following comment on the blog:

I appreciate that you’re endorsing these changes in response to the two specific cases I raised on X (unlimited model retraining and composition with unsafe covered models). My gut sense is still that ad-hoc patching in this manner just isn’t a robust way to deal with the underlying issue*, and that there are likely still more cases like those two. In my opinion it would be better for the bill to adopt a different framework with respect to hazardous capabilities from post-training modifications (something closer to “Covered model developers have a duty to ensure that the marginal impact of training/releasing their model would not be to make hazardous capabilities significantly easier to acquire.”). The drafters of SB 1047 shouldn’t have to anticipate every possible contingency in advance, that’s just bad design.

* In the same way that, when someone notices that their supposedly-safe utility function for their AI has edge cases that expose unforseen maxima, introducing ad-hoc patches to deal with those particular noticed edge cases is not a robust strategy to get an AI that is actually safe across the board.

Nice explanation of MSP and good visuals.

This is surprising!

Were you in fact surprised? If so, why? (This is a straightforward consequence of the good regulator theorem^[1].)

In general I'd encourage you to carefully track claims about transformers, HMM-predictors, and LLMs, and to distinguish between trained NNs and the training process. In this writeup, all of these are quite blended.

This seems related to one of my favorite automation tricks, which is that if you have some task that you currently do manually, and you want to write a script to accomplish that task, you can write a script of the form

echo "Step 1: Fetch the video. Name it video.mp4";
read; # wait for user input
echo "Step 2: Extract the audio. Name it audio.mp3"
read; # wait for user input
echo "Step 3: Break the audio up into overlapping 30 second chunks which start every 15 seconds. Name the chunks audio.XX:XX:XX.mp3"
read; # wait for user input
echo "Step 4: Run speech-to-text over each chunk. Name the result transcript.XX:XX:XX.srt"
read; # wait for user input
echo "Step 5: Combine the transcript chunks into one output file named transcript.srt"
read; # wait for user input

You can then run your script, manually executing each step before pressing "enter", to make sure that you haven't missed a step. As you automate steps, you can replace "print out what needs to be done and wait for the user to indicate t hat the step has completed" with "do the thing automatically".

Unsupervised Feature Detection There is a rich literature on unsupervised feature detection in neural networks.

It might be interesting to add (some of) the literature doing unsupervised feature detection in GANs and in diffusion models (e.g. see recent work from Pinar Yanardag and citation trails). 

Related, I wonder if instead of / separately from the L2 distance, using something like a contrastive loss (similarly to how it was used in NoiseCLR or in LatentCLR) might produce interesting / different results.

I don't buy the argument that safety researchers have unusually good ideas/research compared to capability researchers at top labs

I don't think this particularly needs to be true for my point to hold; they only need to have reasonably good ideas/research, not unusually good, for them to publish less to be a positive thing.

That said, if someone hasn't thought at all about concepts like "differentially advancing safety" or "capabilities externalities," then reading this post would probably be helpful, and I'd endorse thinking about those issues.

That's a lot of what I intend to do with this post, yes. I think a lot of people do not think about the impact of publishing very much and just blurt-out/publish things as a default action, and I would like them to think about their actions more.

[link to about]

Link missing

I think the status quo around publishing safety research is mostly fine (though being a bit more careful seems good); more confidently, I think going as far as the vibe of this post suggests would be bad.

Some possible cruxes, or reasons the post basically didn't move my view on that:

• Most importantly, I think the research published by people working on x-risk tends to overall help safety/alignment more than capabilities.
  • I suspect the main disagreement might be what kind of research is needed to make AI go well, and whether the research currently happening helps.
  • Probably less importantly, I disagree a bit about how helpful that research likely is for advancing capabilities. In particular, I don't buy the argument that safety researchers have unusually good ideas/research compared to capability researchers at top labs (part of this is that my impression is capabilities aren't mainly bottlenecked by ideas, though of course sufficiently good ideas would help).
  • It's getting harder to draw the boundary since people use "safety" or "alignment" for a lot of things now. So, to be clear, I'm talking about research published by people who think there are catastrophic risks from AI and care a lot about preventing those, it seems like that's your target audience.
• Secondarily, longer timelines are only helpful if useful things are happening, and I think if everyone working on x-risk stopped publishing their research, way fewer useful things would happen on the research side. Maybe the plan is to mostly use the additional time for policy interventions? I think that's also complicated though (so far, visibly advancing capabilities have been one of the main things making policy progress feasible). Overall, I think more time would help, but it's not clear how much and I'm not even totally sure about the sign (taking into account worries from hardware overhang).
• I think there are more structural downsides to not publishing anything. E.g. that makes it much harder to get academia on board (and getting academia on board has been pretty important for policy as far as I can tell, and I think getting them even more on board would be pretty good). Not sure this is an actual crux though, if I thought the research that's happening wasn't helpful enough, this point would also be weaker.

I think most of these are pretty long-standing disagreements, and I don't think the post really tries to argue its side of them, so my guess is it's not going to convince the main people it would need to convince (who are currently publishing prosaic safety/alignment research). That said, if someone hasn't thought at all about concepts like "differentially advancing safety" or "capabilities externalities," then reading this post would probably be helpful, and I'd endorse thinking about those issues. And I agree that some of the "But ..." objections you list are pretty weak.

@jessicata [LW · GW] once wrote "Everyone wants to be a physicalist but no one wants to define physics". I decided to check SEP article on physicalism and found that, yep, it doesn't have definition of physics:

Carl Hempel (cf. Hempel 1969, see also Crane and Mellor 1990) provided a classic formulation of this problem: if physicalism is defined via reference to contemporary physics, then it is false — after all, who thinks that contemporary physics is complete? — but if physicalism is defined via reference to a future or ideal physics, then it is trivial — after all, who can predict what a future physics contains? Perhaps, for example, it contains even mental items. The conclusion of the dilemma is that one has no clear concept of a physical property, or at least no concept that is clear enough to do the job that philosophers of mind want the physical to play.

<...>

Perhaps one might appeal here to the fact that we have a number of paradigms of what a physical theory is: common sense physical theory, medieval impetus physics, Cartesian contact mechanics, Newtonian physics, and modern quantum physics. While it seems unlikely that there is any one factor that unifies this class of theories, perhaps there is a cluster of factors — a common or overlapping set of theoretical constructs, for example, or a shared methodology. If so, one might maintain that the notion of a physical theory is a Wittgensteinian family resemblance concept.

This surprised me because I have a definition of a physical theory and assumed that everyone else uses the same.

Perhaps my personal definition of physics is inspired by Engels's "Dialectics of Nature": "Motion is the mode of existence of matter." Assuming "matter is described by physics," we are getting "physics is the science that reduces studied phenomena to motion." Or, to express it in a more analytical manner, "a physicalist theory is a theory that assumes that everything can be explained by reduction to characteristics of space and its evolution in time."

For example, "vacuum" is a part of space with a "zero" value in all characteristics. A "particle" is a localized part of space with some non-zero characteristic. A "wave" is part of space with periodic changes of some characteristic in time and/or space. We can abstract away "part of space" from "particle" and start to talk about a particle as a separate entity, and speed of a particle is actually a derivative of spatial characteristic in time, and force is defined as the cause of acceleration, and mass is a measure of resistance to acceleration given the same force, and such-n-such charge is a cause of such-n-such force, and it all unfolds from the structure of various pure spatial characteristics in time.

The tricky part is, "Sure, we live in space and time, so everything that happens is some motion. How to separate physicalist theory from everything else?"

Let's imagine that we have some kind of "vitalist field." This field interacts with C, H, O, N atoms and also with molybdenum; it accelerates certain chemical reactions, and if you prepare an Oparin-Haldane soup and radiate it with vitalist particles, you will soon observe autocatalytic cycles resembling hypothetical primordial life. All living organisms utilize vitalist particles in their metabolic pathways, and if you somehow isolate them from an outside source of particles, they'll die.

Despite having a "vitalist field," such a world would be pretty much physicalist.

An unphysical vitalist world would look like this: if you have glowing rocks and a pile of organic matter, the organic matter is going to transform into mice. Or frogs. Or mosquitoes. Even if the glowing rocks have a constant glow and the composition of the organic matter is the same and the environment in a radius of a hundred miles is the same, nobody can predict from any observables which kind of complex life is going to emerge. It looks like the glowing rocks have their own will, unquantifiable by any kind of measurement.

The difference is that the "vitalist field" in the second case has its own dynamics not reducible to any spatial characteristics of the "vitalist field"; it has an "inner life."