Doing AI Safety research for ethical reasons.
My webpage.
Leave me anonymous feedback.
I operate by Crocker's Rules.
Posts
Wiki Contributions
Speaking for myself (not my coauthors), I don't agree with your two items, because:
- if your models are good enough at code analysis to increase their insecurity self-awareness, you can use them in other more standard and efficient ways to improve the dataset
- doing self-critique the usual way (look over your own output) seems much more fine-grained and thus efficient than asking the model whether it "generally uses too many try-excepts"
More generally, I think behavioral self-awareness for capability evaluation is and will remain strictly worse than the obvious capability evaluation techniques.
That said, I do agree systematic inclusion of considerations about negative externalities should be a norm, and thus we should have done so. I will shortly say now that a) behavioral self-awareness seems differentially more relevant to alignment than capabilities, and b) we expected lab employees to find out about this themselves (in part because this isn't surprising given out-of-context reasoning), and we in fact know that several lab employees did. Thus I'm pretty certain the positive externalities of building common knowledge and thinking about alignment applications are notably bigger.
Most difficulties you raise here could imo change drastically with tens of billions being injected into AI safety, especially thanks to new ideas coming out of left field that might make safety cases way more efficient. (I'm probably more optimistic about new ideas than you, partly because "it always subjectively feels like there are no big ideas left", and AI safety is so young.)
If your government picks you as a champion and gives you amazing resources, you no longer have to worry about national competition, and that amount seems doable. You still have to worry about international competition, but will you feel so closely tied that you can't even spare that much? My guess would be no. That said, I still don't expect certain lab leaders to want to do this.
The same is not true of security though, that's a tough one.
See our recent work (especially section on backdoors) which opens the door to directly asking the model. Although there are obstacles like Reversal Curse and it's unclear if it can be made to scale.
I have two main problems with t-AGI:
A third one is a definitory problem exacerbated by test-time compute: What does it mean for an AI to succeed at task T (which takes humans X hours)? Maybe it only succeeds when an obscene amount of test-time compute is poured. It seems unavoidable to define things in terms of resources as you do
1Very cool! But I think there's a crisper way to communicate the central point of this piece (or at least, a way that would have been more immediately transparent to me). Here it is:
Say you are going to use Process X to obtain a new Model. Process X can be as simple as "pre-train on this dataset", or as complex as "use a bureaucracy of Model A to train a new LLM, then have Model B test it, then have Model C scaffold it into a control protocol, then have Model D produce some written arguments for the scaffold being safe, have a human read them, and if they reject delete everything". Whatever Process X is, you have only two ways to obtain evidence that Process X has a particular property (like "safety"): looking a priori at the spec of Process X (without running it), or running (parts of) Process X and observing its outputs a posteriori. In the former case, you clearly need an argument for why this particular spec has the property. But in the latter case, you also need an argument for why observing those particular outputs ensures the property for this particular spec. (Pedantically speaking, this is just Kuhn's theory-ladenness of observations.)
Of course, the above reasoning doesn't rule out the possibility that the required arguments are pretty trivial to make. That's why you summarize some well-known complications of automation, showing that the argument will not be trivial when Process X contains a lot of automation, and in fact it'd be simpler if we could do away with the automation.
It is also the case that the outputs observed from Process X might themselves be human-readable arguments. While this could indeed alleviate the burden of human argument-generation, we still need a previous (possibly simpler) argument for why "a human accepting those output arguments" actually ensures the property (especially given those arguments could be highly out-of-distribution for the human).
My understanding from discussions with the authors (but please correct me):
This post is less about pragmatically analyzing which particular heuristics work best for ideal or non-ideal agents in common environments (assuming a background conception of normativity), and more about the philosophical underpinnings of normativity itself.
Maybe it's easiest if I explain what this post grows out of:
There seems to be a widespread vibe amongst rationalists that "one-boxing in Newcomb is objectively better, because you simply obtain more money, that is, you simply win". This vibe is no coincidence, since Eliezer and Nate, in some of their writing about FDT, use language strongly implying that decision theory A is objectively better than decision theory B because it just wins more. Unfortunately, this intuitive notion of winning cannot actually be made into a philosophically valid objective metric. (In more detail, a precise definition of winning is already decision-theory-complete, so these arguments beg the question.) This point is well-known in philosophical academia, and was already succinctly explained in a post by Caspar (which the authors mention).
In the current post, the authors extend a similar philosophical critique to other widespread uses of winning, or background assumptions about rationality. For example, some people say that "winning is about not playing dominated strategies"... and the authors agree about avoiding dominated strategies, but point out that this is not too action-guiding, because it is consistent with many policies. Or also, some people say that "rationality is about implementing the heuristics that have worked well in the past, and/or you think will lead to good future performance"... but these utterances hide other philosophical assumptions, like assuming the same mechanisms are at play in the past and future, which are especially tenuous for big problems like x-risk. Thus, vague references to winning aren't enough to completely pin down and justify behavior. Instead, we fundamentally need additional constraints or principles about normativity, what the authors call non-pragmatic principles. Of course, these principles cannot themselves be justified in terms of past performance (which would lead to circularity), so they instead need to be taken as normative axioms (just like we need ethical axioms, because ought cannot be derived from is).
1Like Andrew, I don't see strong reasons to believe that near-term loss-of-control accounts for more x-risk than medium-term multi-polar "going out with a whimper". This is partly due to thinking oversight of near-term AI might be technically easy. I think Andrew also thought along those lines: an intelligence explosion is possible, but relatively easy to prevent if people are scared enough, and they probably will be. Although I do have lower probabilities than him, and some different views on AI conflict. Interested in your take @Daniel Kokotajlo
You know that old thing where people solipsistically optimizing for hedonism are actually less happy? (relative to people who have a more long-term goal related to the external world) You know, "Whoever seeks God always finds happiness, but whoever seeks happiness doesn't always find God".
My anecdotal experience says this is very true. But why?
One explanation could be in the direction of what Eliezer says here (inadvertently rewarding your brain for suboptimal behavior will get you depressed):
Someone with a goal has an easier time getting out of local minima, because it is very obvious those local minima are suboptimal for the goal. For example, you get out of bed even when the bed feels nice. Whenever the ocasional micro-breakdown happens (like feeling a bit down), you power through for your goal anyway (micro-dosing suffering as a consequence), so your brain learns that micro-breakdowns only ever lead to bad immediate sensations and fixes them fast.
Someone whose only objective is the satisfaction of their own appetites and desires has a harder time reasoning themselves out of local optima. Sure, getting out of bed allows me to do stuff that I like. But those feel distant now, and the bed now feels comparably nice... You are now comparing apples to apples (unlike someone with an external goal), and sometimes you might choose the local optimum. When the ocasional micro-breakdown happens, you are more willing to try to soften the blow and take care of the present sensation (instead of getting over the bump quickly), which rewards in the wrong direction.
Another possibly related dynamic: When your objective is satisfying your desires, you pay more conscious attention to your desires, and this probably creates more desires, leading to more unsatisfied desires (which is way more important than the amount of satisfied desires?).
I agree with conjunctiveness, although again more optimistic about huge improvements. I mostly wanted to emphasize that I'm not sure there are structurally robust reasons (as opposed to personal whims) why huge spendings on safety won't happen