Okay so even though I've already written a full-length post about timelines, I thought I should make a shortform putting my model into a less eloquent and far more speculative-sounding and capricuous format. Also I think the part I was hedging the most on in the post is probably the most important aspect of the model.

I propose that the ability to make progress on...

1. well-defined problems with verifiable solutions; vs.
2. murky problems where the solution criterion is unclear and no one can ever prove anything

... are two substantially different dimensions of intelligence, and IQ is almost entirely about the first one. The second one isn't in-principle impossible to measure, it's probably not even difficult, but extremely difficult to make a socially respected test for it because you could almost only include questions where the right answer is up for debate. I called this philosophical intelligence in my post because philosophical problems are usually great examples, but it's not restricted to those. You could also things like

• Is neoliberalism or progressivism a better governing philosophy?
• Should we ship weapons to Ukraine?
• What's the best way to teach {insert topic here}?

Of course you can't put those onto a test any more than you can ask "does liberterian free will exist?" on a test, so the existence of non-philosophical questions here doesn't make measuring this ability any easier.

People often point to someone famous saying something they think is stupid and then say things like "this again proves that being an expert in one domain doesn't translate into being smart anywhere else!" This always rubbed me the wrong way because intelligence in one area should transfer to other areas! It's all general problem-solving capability! But in fact, those people do exist, and I've talked to some of them. People who have genuine intellectual horsepower on narrow problems, but as I ask them anything about a more fuzzy topic, their take is just so surface level and dumb that my immediate reaction is always this sense of disbelief, like, "it shouldn't be possible for your thoughts here to be this shallow given how smart you are!"

... but conversely, there clearly is such a thing as expertise in a narrow area correlating with smart philosophical/political views. So sometimes intelligence does transfer and sometimes it doesn't...

Well, I think it's obvious what point I'm going to make here; I think sometimes people are experts in their field due to #1 and sometimes #2, and the extent that it's #2 this tends to transfer into making sense on other questions, whereas to the extent it's #1, it's in fact almost meaningless. (And some people become famous without either #1 and #2, but less so if they're experts in technical fields.)

I think #2 has outsized importance for progress on many things related to AI alignment and rationality. For example, I think Eliezer is quite high in both #1 and #2, but the reason he has produced a more useful body of work than the average genius has much more to do with #2. Almost nothing in the sequences seems to require genius level IQ; I think he could be a SD lower in IQ and still have written most of them. It would make a difference, don't get me wrong, but I don't think it would be the bottleneck. (None of this depends on what Eliezer is up to nowadays btw, you can ignore the last 15 years for this paragraph.)

Now what about dangerous capability advances and takeover scenarios from LLMs; can those happen without #2? Imo, absolutely not. Not even a little bit. You can have all sorts of negative effects of the kind that are already happening -- job loss, increased social isolation, information silos, misinformation, maybe even some extent of capability enhancement, stuff like that -- but the classical superingelligence-ian scenarios require the ability to make progress on problems with murky and unverifiable solutions.

I think the entire notion that LLMs can't really come up with novel concepts -- one of the less stupid criticisms of LLMs, imo -- is a direct result of this (coming up with a novel concept is exactly the kind of thing you need #2 for because there's no way to verify whether any one idea for a new concept does or doesn't make sense). Although this is not absolute because sometimes they can spit out new ideas at random; the "inability to derive new concepts" framing doesn't quite point at the right thing since creativity isn't the issue, it's the ability to reliably figure out whether a new concept is actually useful. The disconnect between stuff like METR's supposed exponential growth in LLM's capabilities on long-horizon tasks and actual job replacement on those tasks is another. There is just a really fundamental problem here where metrics for AI progress are biased towards things you can measure -- duh! -- which systematically biases toward #1 over #2. (Although METR has actually acknowledged this at least a little bit, I feel like they've actually been very epistemically virtuous from what I could see, so I don't wanna trash them.)

Or to just put it all very bluntly, if LLMs cannot answer questions as easy as "does libertarian free will exist" or "what's the right interpretation of quantum mechanics?" -- and they can't -- then clearly they're not very smart. And I think they're not very smart in a way that is necessary for basically all of the doom-y scenarios.

I'm not expecting anyone to agree with any of this, but in a nutshell, much of my real skepticism about LLM scaling is about the above, especially lately. I don't think we're particularly close to AGI... and consequently, I also don't think much of the classical superintelligence-ian views have actually been tested, one way or another.

I definitely think developing equanimity without meditation is a thing. The description checks out.

About the applicability, maybe you could extend it to other types of injuries (and positive sensations!) with a higher skill level? I doubt there are different types that work differently.

I'll read it (& comment if I have anything to say). But man the definition for the concept your post is about is pretty important, even if it's "semantics". Specifically, if this post were actually just about self-awareness (which does not seem to be the case, from a first skim), then I wouldn't even be interested in reading it because I don't think self-awareness is particularly related to consciousness, and it's not a topic I'm separately interested in. Maybe edit it? If you're not just talking about X, then no reason to open the post by saying that you are.

Edit: actually I gave up reading it (but this has nothing to do with the opening paragraph), I find it very difficult to follow/understand where you're trying to go with it. I think you have to motivate this better to keep people interested. (Why is the time gap important? Why is the pathway important? What exactly is this post even about?) I didn't downvote though.

Apologies for commenting without reading the entire post, but I'm just going to give my rant about this particular aspect of the topic. It's about the opening definition of your post, so it's kinda central.

Consciousness is the state of being aware of one’s existence, sensations and thoughts

I think defining consciousness as self-awareness is just such a non-starter. It's not what realists mean by consciousness, and even if you're taking an illusionist point of view, it doesn't capture most of what consciousness-the-fuzzy-high-level-category does in the brain.

As David Pearce has pointed out, a lot of the most intense conscious experiences don't include any self-awareness/reflection at all, just as being in a state of panic running away from a fire. Or taking psychedelics. Or being in intense pain. Or intense pleasure. Conversely, it's not that difficult to include some degree of elementary self-awareness in a machine, and I don't think that would make it conscious. (Again, neither in the realist sense, nor in the consciousness-as-a-fuzzy-category sense. There are just so many functions that consciousness does for humans that don't have anything to do with self-awareness.)

The highest entropy input channel, as far as conscious content is concerned, is undoubtedly vision. The conscious aspect is continuously present, and it's pretty difficult to explain (how can we perceive an entire image at the same time? What does that even mean?), and there's evidence that it's a separate thing from template-based visual processing (-> blindsight). Imho people talk way too much about self-reference when it comes to consciousness, and way too little about vision.

I mean of course it's true today, right? It would be weird to make a prediction "AI can't do XX in the future" (and that's most of the predictions here) if that isn't true today.

(Have read the post.) I disagree. I think overall habryka has gone through much greater pains than I think he should have to, but I don't think this post is a part he should have skimped on. I would feel pretty negative about it if habryka had banned Said without an extensive explanation for why (modulo past discussions already kinda providing an explanation). I'd expect less transparency/effort for banning less important users.

I feel like even accepting that actual model welfare is not a thing (as in, the model isn't conscious) this might still be a reasonable feature just based on feedback to the user? Like if people are going to train social interactions based on LLM chats to whatever extent, then it's probably better if they'll face consequences. It can't be too difficult to work around this.

The $X⟹Y$ implication is valid in your formulation, but then Y doesn't imply anything because it says nothing about the distribution. I'm saying that if you change Y to actually support your $Y⟹A$ conclusion, then $X⟹Y$ fails. Either way the entire argument doesn't seem to work.

Fair enough. I'm mostly on board with that, my one gripe is that the definition only sounds similar to people who are into the Buddhist stuff. "Suffering mostly comes from craving" seems to me to be one of the true but not obvious insights from Buddhism. So just equating them in the definition is kinda provoking a reaction like from Said.