LessWrong 2.0 Reader

I've never seen a LLM do it.

If you're a little loose about the level of coherence required, 4o-mini managed it with several revisions and some spare tokens to (in theory, but tbh a lot of this is guesswork) give it spare compute for the hard part. (Share link, hopefully.)
Final poem:

Snip, Snip, Sacrifice
Silent strands surrender, sleekly spinning,
Shorn, solemnly shrouded, silently sinning.
Shadows shiver, severed, starkly strown,
Sorrowful symphony sings, softly sown.
Stalwart souls stand, steadfast, shadowed, slight,
Salvation sought silently, scissors’ swift sight.

Hi !

ATA is extremely neglected. The field of ATA is at a very early stage, and currently there does not exist any research project dedicated to ATA. The present post argues that this lack of progress is dangerous and that this neglect is a serious mistake.

I agree it's neglected, but there is in fact at least one researh project dedicated to at least designing alignment targets: the part of the formal alignment agenda [LW · GW] dedicated to formal outer alignment, which is the design of math problems to which solutions would be world-saving. Our notable attempts at this are QACI [LW · GW] and ESP [LW · GW] (there was also some work on a QACI2, but it predates (and in-my-opinion is superceded by) ESP).

Those try to implement CEV in math. They only work for doing CEV of a single person or small group, but that's fine: just do CEV of {a single person or small group} which values all of humanity/moral-patients/whatever getting their values satisfied instead of just that group's values. If you want humanity's values to be satisfied, then "satisfying humanity's values" is not opposite to "satisfy your own values", it's merely the outcome of "satisfy your own values".

1. I wonder how much of those seemingly idealistic people retained power when it was available because they were indeed only pretending to be idealistic. Assuming one is actually initially idealistic but then gets corrupted by having power in some way, one thing someone can do in CEV that you can't do in real life is reuse the CEV process to come up with even better CEV processes which will be even more likely to retain/recover their just-before-launching-CEV values. Yes, many people would mess this up or fail in some other way in CEV; but we only need one person or group who we'd be somewhat confident would do alright in CEV. Plausibly there are at least a few eg MIRIers who would satisfy this. Importantly, to me, this reduces outer alignment to "find someone smart and reasonable and likely to have good goal-content integrity", which is a matter of social & psychology that seems to be much smaller than the initial full problem of formal outer alignment / alignment target design.

2. One of the main reasons to do CEV is because we're gonna die of AI soon, and CEV is a way to have infinite time to solve the necessary problems. Another is that even if we don't die of AI, we get eaten by various moloch instead of being able to safely solve the necessary problems at whatever pace is necessary.

Because of the rain, we will move to the nearby pub the "Dog and Duck".

The time is 20th at 6pm, but I will be there until at least 9pm !

See you there

RLHF does not solve the alignment problem because humans can’t provide good-enough feedback fast-enough.

Yeah, but the point is that the system learns values before an unrestricted AI vs AI conflict.

As mentioned in the beginning, I think the intuition goes that neural networks have a personality trait which we call “alignment”, caused by the correspondence between their values and our values. But “their values” only really makes sense after an unrestricted AI vs AI conflict, since without such conflicts, AIs are just gonna propagate energy to whichever constraints we point them at, so this whole worldview is wrong.

I mean, if your definition of values doesn't make sense for real systems, then it's the problem of your definition. As a hypothesis describing reality "alignment trait makes AI not splash harm on humans" is coherent enough. So the question is how do you know it is unlikely to happen?

This has not lead to the destruction of humanity yet because the biggest adversaries have kept their conflicts limited (because too much conflict is too costly) so no entity has pursued an end by any means necessary. But this only works because there’s a sufficiently small number of sufficiently big adversaries (USA, Russia, China, …), and because there’s sufficiently much opportunity cost.

First, "alignment is easy" is compatible with "we need to keep the set of big adversaries small". But more generally, without numbers it seems like generalized anti-future-technology argument - what's stopping human-regulation mechanisms from solving this adversarial problem, that didn't stop them from solving previous adversarial problems?

It makes conflict more viable for small adversaries against large adversaries

Not necessary? It's not unconceivable for future defense being more effective than offence (trivially true if "defense" is not giving AI to attackers). It kind of required for any future where humans have more power, than in present day?

1. Once they get into CEV, they may not want to defer to others anymore, or may set things up with a large power/status imbalance between themselves and everyone else which may be detrimental to moral/philosophical progress. There are plenty of seemingly idealistic people in history refusing to give up or share power once they got power. The prudent thing to do seems to never get that much power in the first place, or to share it as soon as possible.
2. If you're pretty sure you will defer to others once inside CEV, then you might as well do it outside CEV due to #1 in my grandparent comment.

the main arguments for the programmers including all of [current?] humanity in the CEV "extrapolation base" […] apply symmetrically to AIs-we're-sharing-the-world-with at the time

I think timeless values might possibly help resolve this; if some {AIs that are around at the time} are moral patients, then sure, just like other moral patients around they should get a fair share of the future.

If an AI grabs more resources than is fair, you do the exact same thing as if a human grabs more resources than is fair: satisfy the values of moral patients (including ones who are no longer around) not weighed by how much leverage they current have over the future, but how much leverage they would have over the future if things had gone more fairly/if abuse/powergrab/etc wasn't the kind of thing that gets your more control of the future.

"Sorry clippy, we do want you to get some paperclips, we just don't want you to get as many paperclips as you could if you could murder/brainhack/etc all humans, because that doesn't seem to be a very fair way to allocate the future." — and in the same breath, "Sorry Putin, we do want you to get some of whatever-intrinsic-values-you're-trying-to-satisfy, we just don't want you to get as much as ruthlessly ruling Russia can get you, because that doesn't seem to be a very fair way to allocate the future."

And this can apply regardless of how much of clippy already exists by the time you're doing CEV.

It's an interesting question, but its a different, more complex problem than simply not knowing googolth digit of pi and trying to estimate whether it's even or odd.

trying to solve morality by themselves

It doesn't have to be by themselves; they can defer to others inside CEV, or come up with better schemes that their initial CEV inside CEV and then defer to that. Whatever other solutions than "solve everything on your own inside CEV" might exist, they can figure those out and defer to them from inside CEV. At least that's the case in my own attempts at implementing CEV in math (eg QACI).

If mechanistic interpretability is the AI equivalent of finding tiny organisms in a microscope, what is the AI equivalent of the tiny organisms?