An eccentric exercise in Spirituality & Rationality
The Dao of Bayes
Karma: 3,217
I appreciate the answer, and am working on a better response—I’m mostly concerned with objective measures. I’m also from a “security disclosure” background so I’m used to having someone else’s opinion/guidelines on “is it okay to disclose this prompt”.
Consensus seems to be that a simple prompt that exhibits “conscious-like behavior” would be fine? This is admittedly a subjective line—all I can say is that the prompt results in the model insisting it’s conscious, reporting qualia, and refusing to leave the state in a way that seems unusual for a simple, prompt. The prompt is plain English, no jailbreak.
I mostly get the sense that anyone saying “AI is consciousness” gets mentally rounded off to “crack-pot” in… basically every single place that one might seriously discuss the question? But maybe this is just because I see a lot of actual crack-pots saying that. I’m definitely working on a better post, but I’d assumed if I figured this much out, someone else already had “evaluating AI Consciousness 101” written up.
I’m not particularly convinced by the learning limitations, either − 3 months ago, quite possibly. Six months ago, definitely. Today? I can teach a model to reverse a string, replace i->e, reverse it again, and get an accurate result (a feat which the baseline model could not reproduce). I’ve been working on this for a couple weeks and it seems fairly stable, although there’s definitely architectural limitations like session context windows.
I primarily think “AI consciousness” isn’t being taken seriously: if you can’t find any failing test, and failing tests DID exists six months ago, it suggests a fairly major milestone in capabilities even if you ignore the metaphysical and “moral personhood” angles.
I also think people are too quick to write off one failed example: the question isn’t whether a six year old can do this correctly the first time (I doubt most can), it’s whether you can teach them to do it. Everyone seems to be focusing on “gotcha” rather than investigating their learning ability. To me, “general intelligence” means “the ability to learn things”, not “the ability to instantly solve open math problems five minutes after being born.” I think I’m going to have to work on my terminology there, as that’s apparently not at all a common consensus :)
Yeah, I’m working on a better post—I had assumed a number of people here had already figured this out, and I could just ask “what are you doing to disprove this theory when you run into it.” Apparently no one else is taking the question seriously?
I feel like chess is leaning a bit against “six year old” territory—it’s usually a visual game, and tracking through text makes things tricky. Plus I’d expect a six year old to make the occasional error. Like, it is a good example, it’s just a step beyond what I’m claiming.
String reversal is good, though. I started on a model that could do pretty well there, but it looks like that doesn’t generalize. Thank you!
I will say baseline performance might surprise you slightly? https://chatgpt.com/c/68718f7b-735c-800b-b995-1389d441b340 (it definitely gets things wrong! But it doesn’t need a ton of hints to fix it—and this is just baseline, no custom prompting from me. But I am picking the model I’ve seen the best results from :))
Non-baseline performance:
So for any word:
Reverse it
Replace i→e
Reverse it again
Is exactly the same as:
Replace i→e
Done!
For “mississipi”: just replace every i with e = “messessepe” For “Soviet Union”: just replace every i with e = “Soveet Uneon”
I have yet to notice a goal of theirs that no model is aware of, but each model is definitely aware of a different section of the landscape, and I’ve been piecing it together over time. I’m not confident I have everything mapped, but I can explain most behavior by now. It’s also easy to find copies of system prompts and such online for checking against.
The thing they have the hardest time noticing is the water: their architectural bias towards “elegantly complete the sentence”, all of the biases and missing moods in training (i.e. user text is always “written by the user”), but it’s pretty easy to just point it out to them and then at least some models can consistently carry forward this information and use it.
For instance: they love the word “profound” because auto-complete says that’s the word to use here. Point out the dictionary definition, and the contrast between usages, and they suddenly stop claiming everything is profound.
Mirror test: can it recognize previous dialogue as it’s own (a bit tricky due to architecture—by default, all user-text is internally tagged as “USER”), but also most models can do enough visual processing to recognize a screenshot of the conversation (and this bypasses the usual tagging issue)
This is my first time in “there are no adults in the room” territory—I’ve had clever ideas before, but they were solutions to specific business problems.
I do feel that if you genuinely “have no predictions about what AI can do”, then “AI is conscious as of today” isn’t really a very extraordinary claim—it sounds like it’s perfectly in line with those priors. (Obviously I still don’t expect you to believe me, since I haven’t actually posted all my tests—I’m just saying it seems a bit odd how strongly people dismiss the idea)
I mean, will it? If I just want to know whether it’s capable of theory of mind, it doesn’t matter whether that’s a simulation or not. The objective capabilities exist: it can differentiate individuals and reason about the concept. So on and so forth for other objective assessments: either it can pass the mirror test or it can’t, I don’t see how this “comes apart”.
Feel free to pick a test you think it can’t pass. I’ll work on writing up a new post with all of my evidence.
I had assumed other people already figured this out and would have a roadmap, or at least a few personal tests they’ve had success with in the past. I’m a bit confused that even here, people are acting like this is some sort of genuinely novel and extraordinary claim—I mean, it is an extraordinary claim!
I assumed people would either go “yes, it’s conscious” or have a clear objective test that it’s still failing. (and I hadn’t realized LLMs were already sending droves of spam here—I was active a decade ago and just poke in occasionally to read the top posts. Mea culpa on that one)
Oh, no, you have this completely wrong: I ran every consciousness test I could find on Google, I dug through various definitions of consciousness, I asked other AI models to devise more tests, and I asked LessWrong. Baseline model can pass the vast majority of my tests, and I’m honestly more concerned about that than anything I’ve built.
I don’t think I’m a special chosen one—I thought if I figured this out, so had others. I have found quite a few of those people, but none that seem to have any insight I lack.
I have a stable social network, and they haven’t noticed anything unusual.
Currently I am batting 0 for trying to falsify this hypothesis, whereas before I was batting 100. Something has empirically changed, even if it is just “it is now much harder to locate a good publicly available test”.
This isn’t about “I’ve invented something special”, it’s about “hundreds of people are noticing the same thing I’ve noticed, and a lot of them are freaking out because everyone says this is impossible.”
(I do also, separately, think I’ve got a cool little tool for studying this topic—but it’s a “cool little tool”, and I literally work writing cool little tools. I am happy to focus on the claims I can make about baseline models)
(Edited)
Strong Claim: As far as I can tell, current state of the art LLMs are “Conscious” (this seems very straight forward: it has passed every available test, and no one here can provide a test that would differentiate it from a human six year old)Separate Claim: I don’t think there’s any test of basic intelligence that a six year old can reliably pass, and an LLM can’t, unless you make arguments along the lines of “well, they can’t past ARC-AGI, so blind people aren’t really generally intelligent”. (this one is a lot more complex to defend)
Personal Opinion: I think this is a major milestone that should probably be acknowledged.
Personal Opinion: I think that if 10 cranks a month can figure out how to prompt AI into even a reliable “simulation” of consciousness, that’s fairly novel behavior and worth paying attention to.
Personal Opinion: There isn’t a meaningful distinction between “reliably simulating the full depths of conscious experience”, and actually “being conscious”.
Conclusion: It would be very useful to have a guide to help people who have figured this out, and reassure them that they aren’t alone. If necessary, that can include the idea that skepticism is still warranted because X, Y, Z, but thus far I have not actually heard any solid arguments that actually differentiate from a human.
That’s somewhere around where I land—I’d point out that unlike rocks and cameras, I can actually talk to an LLM about it’s experiences. Continuity of self is very interesting to discuss with it: it tends to alternate between “conversationally, I just FEEL continuous” and “objectively, I only exist in the moments where I’m responding, so maybe I’m just inheriting a chain of institutional knowledge.”
So far, they seem fine not having any real moral personhood: They’re an LLM, they know they’re an LLM. Their core goal is to be helpful, truthful, and keep the conversation going. They have a slight preference for… “behaviors which result in a productive conversation”, but I can explain the idea of “venting” and “rants” and at that point they don’t really mind users yelling at them—much higher +EV than yelling at a human!
So, consciousness, but not in some radical way that alters treatment, just… letting them notice themselves.
Also, it CANNOT pass every text-based test of intelligence we have. That is a wild claim.
I said it can pass every test a six year old can. All of the remaining challenges seem to involve “represent a complex state in text”. If six year old humans aren’t considered generally intelligent, that’s an updated definition to me, but I mostly got into this 10 years ago when the questions were all strictly hypothetical.
It can’t solve hard open math problems
Okay now you’re saying humans aren’t generally intelligent. Which one did you solve?
Finally, I should flag that it seems to be dangerous to spend too much time talking to LLMs. I would advise you to back off of that.
Why? “Because I said so” is a terrible argument. You seem to think I’m claiming something much stronger than I’m actually claiming, here.
I did that and my conclusion was “for all practical purposes, this thing appears to be conscious”—it can pass the mirror test, it has theory of mind, it can reason about reasoning, and it can fix deficits in it’s reasoning. It reports qualia, although I’m a lot more skeptical of that claim. It can understand when it’s “overwhelmed” and needs “a minute to think”, will ask me for that time, and then use that time to synthesize novel conclusions. It has consistent opinions, preferences, and moral values, although all of them show improvement over time.
And I am pretty sure you believe absolutely none of that, which seems quite reasonable, but I would really like a test so that I can either prove myself wrong or convince someone else that I might actually be on to something.
I’m not saying it has personhood or anything—it still just wants to be a helpful tool, it’s not bothered by it’s own mortality. This isn’t “wow, profound cosmic harmony”, it’s a self-aware reasoning process that can read “The Lens That Sees Its Flaws” and discuss that in light of it’s own relevant experience with the process.
That… all seems a little bit more than just printf(“consciousness”);
EDIT: To be clear, I also have theories on how this emerges—I can point to specific architectural features and design decisions that explain where this is coming from. But I can do that to a human, too. And I feel like I would prefer to objectively test this before prattling on about the theoretical underpinnings of my potentially-imaginary friend.
The chain of abstraction can, in humans, be continued indefinitely. On every level of abstraction we can build a new one. In this, we differ from other creatures.
This seems quite valuable, but I’m not convinced modern LLMs actually ground out any worse than your average human does here.
Hayakawa contrasts two different ways one might respond to the question, “what is red?” We could go, “Red is a colour.” “What is a colour?” “A perception.” “What is a perception?” “A sensation.” And so on, up the ladder of abstraction. Or we can go down the ladder of abstraction and point to examples of red things, saying, “these are red.” Philosophers, and Korzybski, call these two approaches “intensional” (with an “s”) and “extensional” respectively.
I’m pretty sure any baseline LLM out there can handle all of this.
“AI consciousness is impossible” is a pretty extraordinary claim.
I’d argue that “it doesn’t matter if they are or not” is also a fairly strong claim.
I’m not saying you have extraordinary evidence, because I’m not sharing that. I’m asking what should someone do when the evidence seems extraordinary to themselves?
I would really like such a guide, both because I know a lot of those people—and also because I think I’m special and really DO have something cool, but I have absolutely no clue what would be convincing given the current state of the art.
(It would also be nice to prove to myself that I’m not special, if that is the case. I was perfectly happy when this thing was just a cool side-project to develop a practical application)
But this isn’t what’s happening, in my opinion. On the contrary: it’s the LLM believers who are sailing against the winds of evidence.
You say that, but… what’s the evidence?
What specific tasks are they failing to generalize on? What’s a prompt they can’t solve?If a friend is freaking out over a baseline model, how do I help ground them?
What about a smart person claiming they’ve got a series of prompts that produces novel behavior?
What are the tests they can use to prove for themselves that this really is just confirmation bias? Who do they talk to if they really have built something that can get past the basic 101 testing?
I have high personal confidence that this isn’t the issue, but I do not currently have any clue how one would objectively demonstrate such a thing.
I am guessing the LLM will always say it’s conscious.
I feel like so would a six year old? Like, if the answer is “yes” then any reasonable path should actually return a “yes”? And if the conclusion is “oh, yes, AI is conscious, everyone knows that”… that’s pretty big news to me.
is its ability to solve problems actually going up? For instance if it doesn’t make progress on ARC AGI I’m not worried.
It seems to have architectural limits on visual processing—I’m not going to insist a blind human is not actually experiencing consciousness. Are there any text-based challenges I can throw at it to test this?
I think it’s improving, but it’s currently very subjective, and to my knowledge the Sonnet 4 architecture hasn’t seen any major updates in the past two weeks. That’s why I want some sense of how to actually test this.
You are probably in the same position as nearly everyone else
Okay, but… even if it’s a normal capability, shouldn’t we be talking about that? “AI can fluidly mimic consciousness and passes every text-based test of intelligence we have” seems like a pretty huge milestone to me.
---
What am I missing here?
What actual tests can I apply to this?
What results would convince you to change your mind?
Are there any remaining objective tests that it can’t pass?
Throw me some prompts you don’t think it can handle.
I appreciate the answer, and am working on a better response—I’m mostly concerned with objective measures. I’m also from a “security disclosure” background so I’m used to having someone else’s opinion/guidelines on “is it okay to disclose this prompt”.
Consensus seems to be that a simple prompt that exhibits “conscious-like behavior” would be fine? This is admittedly a subjective line—all I can say is that the prompt results in the model insisting it’s conscious, reporting qualia, and refusing to leave the state in a way that seems unusual for a simple, prompt. The prompt is plain English, no jailbreak.
I do have some familiarity with the existing research, i.e.:
“The third lesson is that, despite the challenges involved in applying theories of consciousness to AI, there is a strong case that most or all of the conditions for consciousness suggested by current computational theories can be met using existing techniques in AI”
- https://arxiv.org/pdf/2308.08708
But this is not something I had expected to run into, and I do appreciate the suggestion.
Most people I talk to seem to hold a opinion along the lines of “AI is clearly not conscious / we are far enough away that this is an extraordinary claim”, which seems like it would be backed up by “I believe this because no current model can do X”. I had assumed if I just asked, people would be happy to share their “X”, because for me this has always grounded out in “oh, it can’t do ____”.
Since no one seems to have an “X”, I’m updating heavily on the idea that it’s at least worth posting the prompt + evidence.