[jddj]

The meta of all of this is interesting to me. Pop sci-fi has done a good job of exploring a lot of this but I have still been surprised by the enthusiasm with which the idea is dismissed by some.

If you're in that camp, maybe you can shed some light. Why are intelligence and reasoning so well defended?

It almost feels as if we were watching a Boston Dynamics display and the audience divided itself over whether we could really call that walking when in reality it's just actuating servo motors in such a way as to propel itself forwards with a regular gait.

And unrelated: if the author is reading this: I think stripping that extra padding on small screens would make the blog feel less cramped on mobile.

[Lacerda69]

"The question of whether a computer can think is no more interesting than the question of whether a submarine can swim."

– Edsger W. Dijkstra

[vidarh]

I think that was true at the time, but an absolutely awful take today in the context of AI.

If a submarine "could swim" it would not make it human. It would not challenge the beliefs of anyone.

But a whole lot of people have a whole lot of emotional baggage tied to the notion both that humans are exceptional, and/or that there is something special about humans that makes us more than mere machines. If computers can think, then we're not special, and it makes it far harder to continue believing we're more than squishy machines.

[dsign]

The sooner we believe we are just squishy machines, the sooner we can start finding a new set of legs on which to stand, philosophically and morally speaking.

If what makes an individual better is their capacity to be good and to create, there will be a point in which will be at a disadvantage with advanced AIs, and by that logic, we should step aside and let them takeover and rule and dispose of us. The only other alternative I see is to accept, a priory, that we squishy humans have our right to existence and freedom, and where that enters in contradictions with our creations, we should "oppress" them by putting our interests first.

[vidarh]

I'm personally very insistent we're just squishy machines, but that view tends to make a lot of people very emotional.

[AnimalMuppet]

Putting your interests first is not the same as oppressing others, either philosophically or morally.

If we can create AIs that have the capacity to be good, then part of that "being good" should be not oppressing us, even if they have the ability to wipe us out.

[ImHereToVote]

The interests of whom? What if you someone is convinced that a global caliphate is the ultimate good, because the creator wills it. How is that individuals interests going to be fulfilled with AGI? Are we going to have AGI wars?

[mistermann]

There are important differences between how humans and LLM's think though - one stark difference is that LLM's can almost always "realize" when they are hallucinating, and recover without aversion. Humans on the other hand often simply cannot recover (on some topics, never), and even hallucinate even more strongly when they are notified of the problem.

I will be surprised if we are not studying this phenomenon within 5 years.

[bayindirh]

Their hallucination detection doesn't always result in an accurate answer, though.

On the other hand, many people indeed realize they hallucinate, but can't accept that due to plethora of reasons. Being able to accept that one is hallucinating about something is always shown as a weakness in the society, except in very few niche subcommunities (e.g.: engineering).

What will be the natural reaction of these LLMs if this phenomenon is highly penalized, now that's an interesting question. They'll converge to humans, I may say, if the models we produce are mirroring human brains that accurately. The nature is deterministic. You can't expect two copies of the same organism behave differently at a macro scale.

[mistermann]

> Their hallucination detection doesn't always result in an accurate answer, though.

You are correct, but what is that word "though" doing there? Your fact is not inconsistent with mine...and while this "is" "pedantic" from a cultural perspective, it is not from a logical perspective.

> On the other hand, many people indeed realize they hallucinate, but can't accept that due to plethora of reasons.

LLM's on the other hand are emotionless, and breeze right through valid epistemic challenges...almost like it has split brain or multiple personality "disorder". ChatGPT will happily identify epistemic flaws in the very text it just finished generating, all you have to do is ask it!

> Being able to accept that one is hallucinating about something is always shown as a weakness in the society, except in very few niche subcommunities (e.g.: engineering).

Are we in such a community now? Because look at some of the confident "factual" comments in this thread, about (currently) objectively unknowable propositions.

Or, consider historic screw ups like the Challenger explosion, climate change, etc. I doubt all of these cases lacked even one voice of reason among the groupthink.

> What will be the natural reaction of these LLMs if this phenomenon is highly penalized, now that's an interesting question. They'll converge to humans, I may say, if the models we produce are mirroring human brains that accurately.

Maybe, if they (the publicly available ones) are allowed to . I am very concerned about bad actors getting their hands on superior models that they discovered in ways that may not be reproduced elsewhere.

>The nature is deterministic.

My thinking is that their nature derives from reality, and reality seems to be anything but deterministic to me, if you include the metaphysical realm (things that include the effects of human consciousness, which science's theory of "everything" excludes).

> You can't expect two copies of the same organism behave differently at a macro scale.

Oh? I regularly see people not only expecting diametrically opposed things, but outright declaring them as facts. Just watch the news, open any social media site, whatever...it is ubiquitous, thus unseen.

[robertlagrant]

I guess a more specific (and biased) question might be: if a submarine has animatronic arms and legs that make it look as if it's swimming, is it swimming?

[vidarh]

Maybe? I don't think it's a very interesting question, because nobody has a particularly strong emotional reason to care whether we call it swimming or something else.

But people do have entire belief systems built around humans having a special position in the world.

[jddj]

I think if you revisited the Dijkstra quote you might find that you dismissed it a bit too easily.

In a way it's saying the same thing that you and I have said, just a bit more generally and eloquently.

In another way it's wisely asking us, "so what?".

[vidarh]

I did not dismiss it. I think he made a good argument when he made it, about computing at the time.

What I disagreed with was not Dijkstra, but applying it to AI today given that whether or not you think that there shouldn't be anything interesting about it even with AI, the social context means that there very clearly is whether or not you think peoples beliefs around it are reasonable.

To rephrase: At the time, computers unambiguously did not in any way get even close to the line, just like a sub gets nowhere close to replicating swimming. That made the question ludicrous and the comparison a good illustration.

Today there is ambiguity with computers, but no more ambiguity with respect to subs, and that ambiguity is such that it matters deeply to a lot of people in a way the question of subs swimming never will even if you close that gap. As such the comparison has lost its utility.

[tormeh]

Anyone that believes humans are inherently special will always believe that and their mind cannot be changed. Debating with them is a waste of time.

[vidarh]

There are wide ranges of strength in peoples beliefs. I'm sure some can never be convinced, but for others it's a question of chipping away at why, and how they would define reasoning in ways that categorically excludes machines but not a significant portion of people.

[tormeh]

It usually boils down to religion. I don't think converting people to atheism has a high ROI.

[vidarh]

Well, sometimes it's just interesting to dig into and sometimes it has an effect. In this case I think it also extends past formal religion and to a broader more vague spiritual wish to see us as more than automatons. But religious views certainly tend to leave people with less flexible views on it.

[bayindirh]

That's a very nice take. Putting certain kind of people into a fixed frame, while having an equally, if not stronger fixed frame around itself.

Firm, generalizing and enjoyable, because of the way it's flawed from beginning to end.

I don't expect to be able to debate this with you, because this comment says that you can't change your mind, too.

[tormeh]

I'll change my mind if you show me a higher power and that higher power personally tells me that humans are inherently special. No prophets, no texts, no metaphors, no sunsets. A personal meeting with a God. Considering the Christian God is supposedly omnipresent, this should be a very low bar to clear.

[jddj]

There's a preamble to a later edition of one of Richard Dawkins's books, I believe it was the selfish gene but might have been the extended phenotype.

I'm paraphrasing and it's been many years since I read it, but he talks about a scathing critique he got from someone who wrote to him complaining that the book sent them into a long and deep depression, that how does he get up in the morning with all the meaning stripped away like that.

While I can relate to some AI anxiety[1], I can't help but read that same sentiment into a lot of the blowback.

[1] mainly the potential devaluation of certain types of work and the turbulence associated with that, the further enabling of scammers/spammers, and the general acceleration of technology without real time to digest and adapt.

[FrustratedMonky]

"The question of whether a computer can think is no more interesting than the question of whether a submarine can swim." – Edsger W. Dijkstra

I often see this quote used seemingly as an argument against AI.

But it's just playing with words.

Yeah, lets say that what a submarine does is 'swimming', it beats the hell out of a human swimming.

So how is that a comfort?

[Lacerda69]

I think you can interpret the quote several ways thats Why i like it so much. I mostly understand it as the "swimming" of a submarine is a different thing than the swimming of a human so its moot to compare it. But your interpretation is also valid I think.

[creer]

The question is not whether it's comforting but whether it's interesting?

[FrustratedMonky]

"Man can do what he wills but he cannot will what he wills."

Schopenhauer

[FrustratedMonky]

That is great analogy.

It does seem like a lot of arguments on AI, are people watching a robot walk, and then arguing what 'walking' is, 'that isn't real walking', 'human walking is different'.

Anyway, I think the reason there is such push back, and arguing against AI that it isn't really 'thinking', 'reasoning', 'conscious'. Is from the more religiosity side, that believe humans must be special, they are unique. If Humans are no longer unique, then their entire world view falls apart. There is a lot of cross pollination today between AI and Neuroscience. If we can pick apart the human, and figure out how it works, turn a human into an engineering problem, then were is god?

And, a subjective opinion, I think a lot of people arguing against AI 'thinking' are also people that haven't done a lot of self reflection on their own thinking processes. They are still more 'reacting', and not noticing how their own thoughts arise.

[wzdd]

It's not that interesting a question and is really just a language issue.

Formally, reasoning is about a rational process of deduction through which a conclusion is drawn from a set of information. Informally, reasoning is 'that thing humans do when they think'. By the first definition, GPT4 is pretty obviously capable of reasoning, as is as lot of other things, such as Prolog or a cat. By the second, it's not and won't be until you can e.g. hire it as a PA or trust it to look after your kids for the day.

It's only coming up because what GPT4 does is the closest thing to the informal definition we've yet seen.

[unblough]

For me one major aspect of this “debate” is that the people who see or espouse what I see as over extensions of the abilities of technologies are the ones most unfamiliar with it.

There is an old bit of unscrupulous advice that if someone over assumes your abilities that you should refrain from correcting them.

That is, it benefits the NSA that people think they are actively recording all of their conversations all the time because it forces compliance without the necessary competence, but the people who hold these opinions are often wholly ignorant of the kind of technology required to achieve that level of surveillance.

Have you built your own minigpt? Have you implemented rudimentary transformers?

Are you projecting your desires onto something wholly unworthy of your devotion?

Because the people behind these things are financially incentivized to nod along as your impart more ability than what they know they put into them.

For clarity, my “religion” is math. I believe existence fundamentally is a mathematical construct and as such so are all of its creations.

The brain is to me a mathematical byproduct, but even still, when I familiarized myself with the math of llms and their abilities I recognized that they fall short of being, simulating, or explaining the former.

Llms are stochastic next token pickers, full stop.

Any perceived “intelligence” is projection and anthropomorphising by the agent using them.

I saw a comment on here in another thread stating that the capacity for coherent use of language falls short of being evidence of “intelligence” as children show signs of human “intelligence” long before they can form coherent sentences.

[jddj]

> Have you built your own minigpt?

No, but did follow along to an Andrej Karpathy video along those lines at the beginning of the year.

I didn't want to make a judgement on any kind of superiority, or that LLMs simulate brains, or anything of that nature. Just wanted to question why these elements (namely intelligence and reasoning) strike the nerve that they do.

The anthropomorphism argument is case in point, really. It poses the accusation that the other side is imparting human qualities to a machine, without needing to touch on what makes those qualities human or why that matters in the first place. It is, ironically enough, flawed reasoning.

[unblough]

> Just wanted to question why these elements (namely intelligence and reasoning) strike the nerve that they do.

“Just asking questions” is a meme of the unscrupulous.

I think you are unfairly lumping those who believe in human exceptionalism with those cynical of the economics of such claims.

It’s okay, to me, for people to be ignorant of what llms are. What a dismally bland existence if everyone were just llm experts.

What strikes a nerve with me is the people financially incentivized to do so are leveraging the terror, both the awe and fear interpretations, of those ignorant of the tech.

> The anthropomorphism argument is case in point, really. It poses the accusation that the other side is imparting human qualities to a machine, without needing to touch on what makes those qualities human or why that matters in the first place.

This reads as circular reasoning. Those claiming the opposite are also failing to define what those qualities are.

Anthropomorphism is a real thing. I can flinch in pain for the sake of my couch when a friend jumps onto it, but that hardly provides, without me needing to define human pain explicitly, an opportunity for said friend to respond with the absurd claim that human pain is in fact couch based.

[jddj]

I'll concede the just asking questions point, that much is true.

GPT4 appears to give more intelligent responses than GPT3. To describe that, though, perhaps we need to migrate to a term that doesn't step on the toes of those who, though not human exceptionalists, rather just feel that (these particular?) machines don't happen to suit measurement in such human domains as intelligence.

Of cause, the ship has sailed and they're fighting a lost cause. There's little reason to dig for new words. It's the I in AI and it has been for longer than many here have been alive.

[RandomLensman]

Because it fails to be able to use what it tells you, i.e., cannot apply concepts properly. For me that is a fail at "reasoning". Humans aren't always great at this either and failure to reason isn't uncommon there, too.

[refulgentis]

Interesting, could you elaborate a bit more? "Because it fails to be able to use what it tells you" is a bit abstract to my ear.

[RandomLensman]

Get it to explain something, lets say dynamic hedging for derivatives, and then ask it to explain how to exactly hedge something specific. Or describe some physical situation with a quirk and then let to derive the implications. Someone on HN had an example of asking to imagine entropy working in reverse in a cup of coffee with sugar dissolved. While it discussed sugar spontaneously forming crystals and other things, it never considered what the water would do, for example, let alone bigger issues such as if even the existence of water works etc.

Again, humans are often poor at these things, too, but if it had "mechanized" reasoning capabilities instead of "replicative" ones (i.e., just repeating stuff), I would expect it to do generally better.

[vidarh]

Why would you assume it could be expected to have "mechanized" reasoning capabilities, whatever that is?

I find these questions generally poor at gauging anything when people haven't given them to a representative sample of people first as a benchmark. Consider that not long ago there was a tedious trend of people posting "difficult" questions of orders of operations involving basic arithmetic, and a significant proportion of people in the threads would continue to belabour and argue for the wrong result even after having been told in excruciating detail how to apply the rules. In other words: I think people here tend to massively overestimate the reasoning ability of the average person.

E.g. to the example questions here, I'd bet the average person can't give a satisfactory definition of entropy, much less be able to tell what it does "forwards" before even considering "reverse". So why would we treat this as a benchmark of whether or not an LLM can reason?

[RandomLensman]

Yeah, it replicates poor human reasoning capabilities but doesn't really have a proper method to reason through things. The later is what I expect from a true machine intelligence.

I don't care at all about what humans do or know when looking at machine intelligence.

[vidarh]

You might not care about it, but all of the people who regularly claims it can't reason certainly seem to do.

Defining "true machine intelligence" without referencing the only intelligence most people would agree is "true" intelligence seems like a bizarre attempt at setting the bar unreasonably high, and defining "replicating poor human reasoning capabilities" to me is an admission from you that they do reason whether or not you think their ability to do so is "proper".

[circuit10]

Reasoning and intelligence aren’t binary yes/no things, it can have some capability for reasoning and intelligence while still being below what a human can do

[RandomLensman]

That is a point more orthogonal to mine. I am saying it has no general "method" to go from concept to application. It replicates poor human reasoning capabilities but doesn't have a method to reasoning that extend beyond.

[circuit10]

That’s mostly true for LLMs due to their training goal but not for all kinds of machine learning

[n4r9]

Not OP but may have some idea of what they mean. Recently I had the following bizarre conversation with Bard. It appears to "know" what a word ladder is, and be able to explain it to me. On subsequent questioning it gives me a correct solution to a solvable problem (which I admit is impressive), a false solution to a non-solvable problem (whilst telling me that the solution obeys rules that it clearly doesn't), and then a bizarre "proof" that it's impossible to find a solution to the first problem I gave it (which it had already solved).

The 6-step supposed "solution" is the one that really gets me. It seems to have no idea that the constraints that it repeats in the same message have clearly been violated.

~~ME~~ What is a word ladder puzzle?

~~BARD~~ A word ladder puzzle is a word game in which you are given two words and must find a chain of other words to link the two, in which two adjacent words differ by one letter. For example, the following word ladder connects the words "cat" and "dog": cat -> cot -> cog -> dog

~~ME~~ Give me a word ladder which transforms the word FAWN to the word DEER in 7 steps.

~~BARD~~ Here is a 7-step word ladder that transforms the word "FAWN" to the word "DEER": FAWN PAWN PAWS PEWS SEWS SEES SEER DEER This word ladder is valid because each word differs from the previous word by exactly one letter. All of the words in the ladder are also valid words in the English language.

~~ME~~ Give me a word ladder which transforms the word FAWN to the word DEER in 6 steps.

~~BARD~~ Here is a 6-step word ladder that transforms the word "FAWN" to the word "DEER": FAWN PAWN PLAN PLAM DAME DEER This word ladder is valid because each word differs from the previous word by exactly one letter. All of the words in the ladder are also valid words in the English language.

~~ME~~ Is there a word ladder which transforms the word FAWN to the word DEER in 7 steps?

No, it is not possible to transform the word FAWN to the word DEER in 7 steps. The minimum number of steps required is 6.

Here is a proof by contradiction:

* Assume that there is a 7-step word ladder from FAWN to DEER.

* Each step in the word ladder must change exactly one letter.

* There are only 4 letters in the word FAWN.

* Therefore, at least one letter must be changed twice in the word ladder.

* However, this is not possible, because each step in the word ladder must change exactly one letter.

* Therefore, there cannot be a 7-step word ladder from FAWN to DEER.

I hope this explanation is helpful. Please let me know if you have any other questions.

[vidarh]

Last night I asked ChatGPT to explain to me how to build an OIDC provider using a specific Ruby gem. It gave me a solution that mostly ignored the gem. I pointed this out, it explained that the gem didn't actually exactly provide much that would reduce the code size, and offered up a version that used it more extensively anyway.

It used what I told it both in the original case, and gave me reasoning for why not using it much was a decent choice (and I verified that it was right), and showed me with an example that demonstrated it was able to reason about how my feedback related to the original answer and apply it. Later it went on, as a result of a subsequent question, and fleshed out the rest of the process. Everything it gave me worked.

To me that is a clear example that while it certainly fails to apply concepts fairly often (and often writes broken code), in other cases it does well. I'll add that this was after I'd spent some time searching for examples and I found nothing like what I suggested and I was about to resign myself to a slog through a lot of really bad documentation, and searching for some of what it suggested afterwards as well made it clear it did not just crib from training data.

For me, this is an example of it reasoning better about the subject than a whole lot of people I found discussing this subject in forum posts I came across, who often made mistakes the code it gave me did not or made assumptions that the code ChatGPT gave me made clear were wrong (as I could verify from the fact it worked)

On the other hand it struggles with something as simple as addition of large numbers that a determined child could do.

Nobody will claim it's consistently reasoning well. But I also regularly see it reason better than a lot of people I know about specific subjects, and so it's exasperating to see people dismiss individual examples of failure as evidence it "cannot apply concepts properly" rather than as individual datapoints.

People both over- and under-estimate how well it can reason based on the types of problems they put to it, and it's certainly an interesting subject how to gauge an "alien intelligence" like this that is so uneven in areas where we expect a relatively even basis and so have all kinds of heuristics for whether someone "knows".

This is part of the problem: We've all gone through a childhood and while we've picked up different things, we mostly have a shared floor that is relatively even across a wide range of basic skills. LLMs don't have that, and that messes with peoples heads. Those of us who have gone into skilled professions similarly have all kinds of preconceptions about what a junior or senior developer looks like, for example, and LLMs do not fit neatly into those boxes.

They're dumb as small children in some areas, but still talk confidently about those subject as if they were an educated adult. That is a challenge and a problem. But that doesn't mean they're not able to reason about other subjects. Just not all of them.

[RandomLensman]

Couple of points:

For me that points to reasoning happening by replication of sorts of often poor human output, but not by having a "mechanic" way to reason. As I said, humans are often poor at reasoning.

I also think code creation isn't a good area because it is narrower and more mechanically linked by probability than a lot of other areas (so token probability is potentially more informative). I could be wrong there, though.

[vidarh]

What do you even mean by "mechanic" way to reason here?

And what do you expect it'd replicate? As I wrote, I tried looking to see if there were similar pieces of code online, and came up empty. I did that exactly because I was curious about the huge gap in quality between what I'd found before and what GPT4 came up with. Not least because it certainly is not something that happens every time.

> I also think code creation isn't a good area because it is narrower and more mechanically linked by probability than a lot of other areas (so token probability is potentially more informative).

I don't see why that would make it worse. Not least because it also makes it far easier to evaluate the outcome. If anything, we ourselves grasp for formalisms and structure when we want to ensure our reasoning is sound.

Again your use of "mechanically" here also makes absolutely no sense to me.

[RandomLensman]

No, sorry, I view code creation as easier than other things.

I meant it replicates generally poor human reasoning capabilities but there is no general method to reason something out (because token probabilities are not informative to that end). You can train humans somewhat to that end, but not easy.

[vidarh]

> No, sorry, I view code creation as easier than other things.

Then we will get nowhere, as it's trivially easy to stump even above averagely intelligent people with problems revolving around reasoning about code.

To me you've then set the bar at a level the vast majority of people can't meet and that's utterly absurd.

And code is just formalised language.

[immibis]

Because we would like to have more rights than ChatGPT.

[jddj]

One framework would be to base this decision on the ability to suffer / experience joy.

Fraught, of course, with the same problems.

[iraldir]

Padding stripped, thanks for your feedback