Derek Shiller

Digi­tal Con­scious­ness Model launch events

• Derek Shiller 13 Jan 2026 14:46 UTC

  4 points

  0 ∶ 0

  on: One rea­son why we might be es­pe­cially un­cer­tain about AI welfare

  This last part carries a lot of weight; a simulacrum, when dormant in the superposition from which it can be sampled, is nonexistent. A simulacrum only exists during the discrete processing event which correlates with its sampling.

  There seems to me to be a sensible view on which a simulacrum exists to the extent that computations relevant to making decisions on its behalf are carried out, regardless of what the token sampler chooses. This would suggest that there could conceivably be vast numbers of different simulacra instantiated even in a single forward pass.

  One odd upshot of requiring the token sampler is that in contexts in which no tokens get sampled (prefill, training) you can get all of the same model computations but have no simulacra at all.

• Derek Shiller 20 Nov 2025 19:36 UTC

  4 points

  0 ∶ 0

  in reply to: Zach Stein-Perlman’s comment on: Longview’s Emerg­ing Challenges Fund can effec­tively ab­sorb marginal funding

  I find this distinction kind of odd. If we care about what digital minds we produce in the future, what should we be doing now?

  I expect that what minds we build in large numbers in the future will be largely depend on how we answer a political question. The best way to prepare now for influencing how we as a society answer that question (in a positive way) is to build up a community with a reputation for good research, figure out the most important cruxes and what we should say about them, create a better understanding of what we should actually be aiming for, initiate valuable relationships with potential stakeholders based on mutual respect and trust, creating basic norms about human-ai relationships, and so on. To me, that looks like engaging with whether near-future AIs are conscious (or have other morally important traits) and working with stakeholders to figure out what policies make sense at what times.

  Though I would have thought the posts you highlighted as work you’re more optimistic about fit squarely within that project, so maybe I’m misunderstanding you.

[Question] Cause prio cruxes in 2026?

• Derek Shiller 7 Nov 2025 17:51 UTC

  10 points

  4 ∶ 0

  on: In­com­pa­ra­bil­ity Im­plies Nihilism

  I think this is basically right (I don’t think the upshot is that incomparability implies nihilism, but rather the moral irrelevance of most choices). I don’t really understand why this is a reason to reject incomparability. If values are incomparable, it turns out that the moral implications are quite different from what we thought. Why change your values rather than your downstream beliefs about morally appropriate action?

• Derek Shiller 21 Aug 2025 12:25 UTC

  2 points

  0 ∶ 0

  in reply to: MinusGix’s comment on: Deep Democ­racy as a promis­ing tar­get for pos­i­tive AGI futures

  Thanks for the suggestion. I’m interested in the issue of dealing with threats in bargaining.

  I don’t think we ever published anything specifically on the defaults issue.

  We were focused on allocating a budget that respects the priorities of different worldviews. The central thing we were encountering was that we started by taking the defaults to be the allocation you get by giving everyone their own slice of the total budget and spending it as they wanted. Since there are often options that are well-suited to each different worldview, there is no way to get good compromises. Everyone is happier with the default than any adjustment of it. (More here.) On the other hand, if you switch the default to be some sort of neutral 0 value (assuming that can be defined), then you will get compromises, but many bargainers would rather that they just be given their own slice of the total budget to allocate.

  I think the importance of defaults comes through just by playing around with some numbers. Consider the difference between setting the default to be the status quo trajectory we’re currently on and setting the default to be the worst possible outcome. Suppose we have two worldviews, one of which cares about suffering in all other people linearly, and the other of which is very locally focused and doesn’t care about immense suffering elsewhere. For the two worldviews, relative to the status quo, option A might give (worldview1: 2,worldview2: 10) value and option B might give (4,6) value. Against this default, option B has a higher product (24 vs 20) and is preferred by Nash bargaining. However, relative to the worst possible value default, option A might give (10,002, 12) and option B (10,004, 8), then option A would be preferred to option B (~120k vs 80k).

• Derek Shiller 20 Aug 2025 19:31 UTC

  9 points

  3 ∶ 0

  in reply to: tylermjohn’s comment on: Deep Democ­racy as a promis­ing tar­get for pos­i­tive AGI futures

  We implemented a Nash bargain solution in our moral parliament and I came away the impression that the results of Nash bargaining are very sensitive to your choice of defaults and for plausible defaults true bargains can be pretty rare. Anyone who is happy with defaults gets disproportionate bargaining power. One default might be ‘no future at all’, but that’s going to make it hard to find any bargain with the anti-natalists. Another default might be ‘just more of the same’, but again, someone might like that and oppose any bargain that deviates much. Have you given much thought to picking the right default against which to measure people’s preferences? (Or is the thought that you would just exclude obstinate minorities?)

• Derek Shiller 9 Aug 2025 17:23 UTC

  4 points

  1 ∶ 1

  on: Why I’m A Fa­natic!

  Keeping the world around probably does that, so you should donate to Longtermist charities (especially because they potentially increase the number of people ever born, thus giving more people a chance of getting into heaven).

  I often get the sense that people into fanaticism think that it doesn’t much change what they actually should support. That seems implausible to me. Maybe you should support longtermist causes. (You probably have to contort yourself to justify giving any money to shrimp welfare.) But I would think the longtermist causes you should support will also be fairly different from ‘mainstream’ causes, and look rather weird close up. You don’t really care if the species colonizes the stars and the future is full of happy people living great lives. If some sort of stable totalitarian hellscape offers a marginally better (but still vanishingly small) chance of producing infinite value, that is where you should put your money.

  Maybe the best expected value would be to tile the universe with computers trying to figure out the best way to produce infinite value under every conceivable metaphysical scheme consistent with what we know and run them all until the heat death of the universe before trying to act. Given that most people are almost certainly not going to do that, you might think that we shouldn’t be looking to build an aligned AI, we should want to build a fanatical AI.

  Has your fanaticism changed your mind much about what is worth supporting?

• Derek Shiller 10 Jul 2025 21:36 UTC

  4 points

  2 ∶ 0

  on: Fish Feel Pain

  But even a 10% chance that fish feel pain—and that we annually painfully slaughter a population roughly ten times the number of humans who have ever lived—is enough to make it a serious issue. Given the mind-bending scale of the harm we inflict on fish, even a modest chance that they feel pain is enough.

  Completely in agreement here.

  And while it’s possible that evolution produced some kind of non-conscious signal that produces identical behavior to pain, such a thing is unlikely. If a creature didn’t feel pain, it’s unlikely it would respond to analgesics, seek out analgesic drugs, and get distracted by bodily damage.

  This is where I would disagree. I expect moderately-complicated creatures would develop traits like these under evolutionary pressures (except seeking out analgesic drugs). The question then is how likely is it that the best /​ only /​ easiest-to-evolve way to produce this slate of behaviors involves having a conscious experience with the relevant pain profile.

  We know that human brains have undergone massive changes since our most recent common ancestor with fish, that terrestrial environments place very different demands on our bodies, that human beings have an unparalleled behavioral flexibility to address injuries, etc. so it is plausible that we do have fairly different nociceptive faculties. It seems to me like a pretty open question precisely how neurologically or algorithmically similar our faculties are and how similar they would need to be to for fish to qualify as having pain. The fact that we can’t even tell how important the cortex is for pain in humans seems like strong evidence that we shouldn’t be too confident about attributing pain to fish. We just know so little. Of course, we shouldn’t be confident about denying it to them either, but much confidence either way seems unjustifiable.

• Derek Shiller 1 Jul 2025 20:43 UTC

  4 points

  0 ∶ 0

  in reply to: David Mathers🔸’s comment on: De­bate: De­pop­u­la­tion Matters

  I would think the trend would also need to be evenly distributed. If some groups have higher-than-replacement birth rates, they will simply come to dominate over time.

• Derek Shiller 24 Jun 2025 18:50 UTC

  14 points

  3 ∶ 0

  in reply to: Bentham's Bulldog’s comment on: De­bate: Mo­ral­ity is Objective

  I think of moral naturalism as a position where moral language is supposed to represent things, and it represents certain natural things. The view I favor is a lot closer to inferentialism: the meaning of moral language is constituted by the way it is used, not what it is about. (But I also don’t think inferentialism is quite right, since I’m not into realism about meaning either.)

  I guess I don’t quite see what your puzzlement is with morality. There are moral norms which govern what people should do. Now, you might deny there in fact are such things, but I don’t see what’s so mysterious.

  Another angle on the mystery: it is possible that there are epistemic norms, moral norms, prudential norms, and that’s it. But if you’re a realist, it seems like it should also be possible that there are hundreds of other kinds of norms that we’re completely unaware of, such that we act in all sorts of wrong ways all the time. Maybe there are special norms governing how you should brush your teeth (that have nothing to do with hygiene or our interests), or how to daydream. Maybe these norms hold more weight than moral norms, in something like the way moral norms may hold more weight than prudential norms. If you’re a non-naturalist, then apart from trust in a loving God, I’m not sure how you address this possibility. But it also seems absurd that I should have to worry about such things.

• Derek Shiller 24 Jun 2025 16:44 UTC

  25 points

  7 ∶ 0

  on: De­bate: Mo­ral­ity is Objective

  I consider myself a pretty strong anti-realist, but I find myself accepting a lot of the things you take to be problems for anti-realism. For instance:

  But lots of moral statements just really don’t seem like any of these. The wrongness of slavery, the holocaust, baby torture, stabbing people in the eye—it seems like all these things really are wrong and this fact doesn’t depend on what people think about it.

  I think that these things really are wrong and don’t depend on what people think about it. But I also think that that statement is part of a language game dictated by complex norms and expectations. The significance of thought experiments. The need to avoid inconsistency. The acceptance of implications. The reliance on gut evaluations. Endorsement of standardly accepted implications. Etc. I live my life according to those norms and expectations, and they lead me to condemn slavery and think quite poorly of slavers and say things like ‘slavery was a terrible stain on our nation’. I don’t feel inclined to let people off the hook by virtue of having different desires. I’m quite happy with a lot of thought and talk that looks pretty objective.

  I’m an anti-realist because I have no idea what sort of thing morality could be about that would justify the norms and expectations that govern our thoughts about morality. Maybe this is a version of the queerness argument. There aren’t any sorts of entities or relations that seem like appropriate truth-makers for moral claims. I have a hard time understanding what they might be such that I would have any inclination to shift what I care about were I to learn that the normative truths themselves were different (holding fixed all of the things that currently guide my deployment of moral concepts). If my intuitions about cases were the same, if all of the theoretical virtues were the same, if the facts in the world were the same, but an oracle were to tell me that moral reality were different in some way—turns out, baby torture is good! -- I wouldn’t be inclined to change my moral views at all. If I’m not inclined to change my views except when guided by things like gut feelings, consistency judgments, etc. then I don’t see how anything about the world can be authoritative in the way that realism should require.

  What links here?

  • Richard Y Chappell🔸's comment on De­bate: Mo­ral­ity is Objective by Bentham's Bulldog (24 Jun 2025 18:19 UTC; 28 points)

• Derek Shiller 26 Apr 2025 20:10 UTC

  5 points

  2 ∶ 0

  on: It’s time to say good­bye to “func­tion­ally equiv­a­lent ar­tifi­cial neu­rons”

  I don’t think it’s even necessary to debate whether quantum phenomena manifest somehow at the macro level of the brain

  You might think it is important that the facts about consciousness contribute to our beliefs about them in some way. Our beliefs about consciousness are surely a phenomenon of the macro level. So if our beliefs are somehow sensitive to the facts, and the facts consist of quantum effects, we should expect those quantum effects to generate some marcoscopic changes.

  This is the sticking point for me with quantum theories: there doesn’t seem to be any obvious mechanism for general quantum level truths to exert the kinds of very targeted influences that would be necessary for them to explain our beliefs about consciousness. And if they don’t, then it seems like we’re left with beliefs insensitive to the truth, and that is deeply unintuitive. What do you think?

• Derek Shiller 18 Apr 2025 17:02 UTC

  17 points

  8 ∶ 1

  in reply to: Chris Leong’s comment on: case­bash’s Shortform

  Also, it is worrying if the optimists easily find financial opportunities that depend on them not changing their minds. Even if they are honest and have the best of intentions, the disparity in returns to optimism is epistemically toxic.

Do­ing Pri­ori­ti­za­tion Better

• Derek Shiller 14 Apr 2025 14:21 UTC

  4 points

  0 ∶ 0

  in reply to: Vasco Grilo🔸’s comment on: Re­think Pri­ori­ties’ Cross-Cause Cost-Effec­tive­ness Model: In­tro­duc­tion and Overview

  Yeah, that’s right. Some kinds of mitigation will increase risks later (e.g. a pause), and the model doesn’t accommodate such nuance.

• Derek Shiller 14 Apr 2025 14:19 UTC

  4 points

  0 ∶ 0

  in reply to: Vasco Grilo🔸’s comment on: Re­think Pri­ori­ties’ Digi­tal Con­scious­ness Pro­ject Announcement

  Could you link the most relevant piece you are aware of? What do you mean by “independently”? Under hedonism, I think the probability of consciousness only matters to the extent it informs the probability of valences experiences.

  The idea is more aspirational. I’m not really sure of what to recommend in the field, but this is a pretty good overview: https://​​arxiv.org/​​pdf/​​2404.16696

  Interesting! How?

  Perhaps valence requires something like the assignment of weights to alternative possibilities. If you can look inside the AI and confirm that it is making decisions in a different way, you can conclude that it doesn’t have valenced experiences. Valence plausibly requires such assignments of weights (most likely with a bunch of other constraints), and the absence of one requirement is enough to disconfirm something. Of course, this sort of requirement is likely to be controversial, but it is less open to radically different views than consciousness itself.

• Derek Shiller 28 Mar 2025 12:48 UTC

  4 points

  0 ∶ 0

  in reply to: Vasco Grilo🔸’s comment on: Re­think Pri­ori­ties’ Digi­tal Con­scious­ness Pro­ject Announcement

  Not at the moment. Consciousness is tricky enough as it is. The field is interested in looking more closely at valence independently of consciousness, given that valence seems more tractable and you could at least confirm that AIs don’t have valenced experience, but that lies a bit outside our focus for now.

  Independently, we’re also very interested in how to capture the difference between positive and negative experiences in alien sorts of minds. It is often taken for granted based on human experience, but it isn’t trivial to say what it is.

• Derek Shiller 19 Mar 2025 12:54 UTC

  10 points

  2 ∶ 0

  in reply to: tylermjohn’s comment on: ...but is in­creas­ing the value of fu­tures tractable?

  This more or less conforms to why I think trajectory changes might be tractable, but I think the idea can be spelled out in a slightly more general way: as technology develops (and especially AI), we can expect to get better at designing institutions that perpetuate themselves. Past challenges to affecting a trajectory change come from erosion of goals due to random and uncontrollable human variation and the chaotic intrusion of external events. Technology may help us make stable institutions that can continue to promote goals for long periods of time.

Beyond Ex­tinc­tion: Re­vis­it­ing the Ques­tion and Broad­en­ing Our View