> It's not clear that equating organic, and synthetic thought will have any meaningful outcome at all,

I agree! I'm saying "If we equate them, we shortcut all the good stuff, e.g., understanding", because "it may be that this tech produces what we can, but that doesn't mean we are the same", which is good because it keeps us learning vs reducing all of "thinking" to just "Whatever latest chatgpt does". We have to continue to believe there is more to thinking, if only because it pushes us to make it better and to keep "us" as the benchmark.

Perhaps I chose the wrong words, but in essence what I'm saying is that giving up agency to a machine that was built to mimic our agency (by definition as a ML system) should be avoided at all costs.

This is complete nonsense.

If you do math in your head or math with a pencil/paper or math with a pocket calculator or with a spreadsheet or in a programming language, it is all the same thing.

The only difference with LLMs is the anthropomorphization of the tool.

agreed.

also, sorry but you (fellow) nerds are terrible at naming.

while "thunking" possibly name-collides with "thunks" from CS, the key is that it is memorable, 2 syllables, a bit whimsical and just different enough to both indicate its source meaning as well as some possible unstated difference. Plus it reminds me of "clunky" which is exactly what it is - "clunky thinking" aka "thunking".

And frankly, the idea it's naming is far bigger than what a "thunk" is in CS

.

Yes, worms think, let the computers have thinking too, the philosophers can still argue all they want about consciousness.

Humans are special, we emit meaning the way stars emit photons, we are rare in the universe as far as empirical observation has revealed. Even with AGI the existence of each complex meaning generator will be a cosmic rarity.

For some people that seems to be not enough, due to their factually wrong word views they see themselves as common and worthless (when they empirically aren't) and need this little psychological boost of unexaminable metaphysical superiority.

But there is an issue of course, the type of thinking humans do is dangerous but net positive and relatively stable, we have a long history where most instantiations of humans can persist and grow themselves and the species as a whole, we have a track record.

These new models do not, people have brains that as they stop functioning they stop persisting the apparatus that supports the brain and they die, people tend to become less capable and active as their thinking deteriorates and hold less influence ocer others accept in rare cases.

This is not the case for an LLM, they seem to be able to hallucinate endlessly and as they have access to the outside world maintain roughly their same amount of causal leverage, their clarity and accuracy of their thinking isn't tied to their persisting.

What does it mean to assume consciousness has no manifestation even in the case of humans? Is that denying that we have an experience of sensation like colors, sounds, or that we experience dreaming, memories, inner dialog, etc?

That's prima facie absurd on the face of it, so I don't know what it means. You would have to a philosophical zombie to make such an argument.

Close. Clanking.

Hear, hear!

I have long thought this, but not had as good way to put it as you did.

If you think about geniuses like Einstein and ramanujen, they understood things before they had the mathematical language to express them. LLMs are the opposite; they fail to understand things after untold effort, training data, and training.

So the question is, how intelligent are LLMs when you reduce their training data and training? Since they rapidly devolve into nonsense, the answer must be that they have no internal intelligence

Ever had the experience of helping someone who's chronically doing the wrong thing, to eventually find they had an incorrect assumption, an incorrect reasoning generating deterministic wrong answers? LLMs dont do that; they just lack understanding. They'll hallucinate unrelated things because they dont know what they're talking about - you may have also had this experience with someone :)

Animals think but come with instincts which breaks the output relative to the input test you propose. Behaviors are essentially pre-programmed input from millions of years of evolution, stored in the DNA/neurology. The learning thus typically associative and domain-specific, not abstract extrapolation.

A crow bending a piece of wire into a hook to retrieve food demonstrates a novel solution extrapolated from minimal, non-instinctive, environmental input. This kind of zero-shot problem-solving aligns better with your definition of intelligence.

I'm not sure I understand what you're getting at. You seem to be on purpose comparing apples and oranges here: for an AI, we're supposed to include the entire training set in the definition of its input, but for a human we don't include the entirety of that human's experience and only look at the prompt?

That an okay-ish definition, but to me this is more about whether this kind of "intelligence" is worth it, not whether it is intelligence itself. The current AI boom clearly thinks it is worth to put that much input to get the current frontier-model-level of output. Also, don't forget the input scales across roughly 1B weekly users at inference time.

I would say a good definition has to, minimally, take on the Turing test (even if you disagree, you should say why). Or in current vibe parlance, it does "feel" intelligent to many people--they see intelligence in it. In my book this allows us to call it intelligent, at least loosely.

There are plenty of humans that will never "get" calculus, despite numerous attempts at the class and countless hours of 1:1 tutoring. Are those people not intelligent? Do they not think? We could say yes they aren't, but by the metric of making money, plenty of people are smart enough to be rich, while college math professors aren't. And while that's a facile way of measuring someone's worth or their contribution to society (some might even say "bad"), it remains that even if someone cant understand calculus, some of them are intelligent enough to understand humans enough to be rich through some fashion that wasn't simply handed to them.

Yeah, that's compression. Although your later comments neglect the many years of physical experience that humans have as well as the billions of years of evolution.

And yes, by this definition, LLMs pass with flying colours.

This feels too linear. Machines are great at ingesting huge volumes of data, following relatively simple rules and producing optimized output, but are LLMs sufficiently better than humans at finding windy, multi-step connections across seemingly unrelated topics & fields? Have they shown any penchant for novel conclusions from observational science? What I think your ratio misses is the value in making the targeted extrapolation or hypothesis that holds up out of a giant body of knowledge.

For more on this perspective, see the paper On the measure of intelligence (F. Chollet, 2019). And more recently, the ARC challenge/benchmarks, which are early attempts at using this kind of definition in practice to improve current systems.

Is the millions of years of evolution part of the training data for humans?

Not quite pointless - something we have established with the advent of LLMs is that many humans have not attained general intelligence. So we've clarified something that a few people must have been getting wrong, I used to think that the bar was set so that almost all humans met it.

I think it has a practical, easy definition. Can you drop an AI into a terminal, give it the same resources as a human, and reliably get independent work product greater than that human would produce across a wide domain? If so, it's an AGI.

I agree that the term can muddy the waters, but as a shorthand for roughly "an agent calling an LLM (or several LLMs) in a loop producing similar economic output as a human knowledge-worker", then it is useful. And if you pay attention to the AI leaders, then that's what the defintion has become.

I agree with almost all of this.

IMO the issue is we won't be able to adequately answer this question before we first clearly describe what we mean of conscious thinking applied to ourselves. First we'd need to clearly define our own consciousness and what we mean by our own "conscious thinking" in a much, much clearer way than we currently do.

If we ever reach that point, I think we'd be able to fruitfully apply it to AI, etc., to assess.

Unfortunately we haven't been obstructed from answering this question about ourselves for centuries or millennia, but have failed to do so, so it's unlikely to happen suddenly now. Unless we use AIs to first solve that problem of defining our own consciousness, before applying it back on them. Which would be a deeply problematic order, since nobody would trust a breakthrough in the understanding of consciousness that came from AI, that is then potentially used to put them in the same class and define them as either thinking things or conscious things.

Kind of a shame we didn't get our own consciousness worked out before AI came along. Then again, wasn't for the lack of trying… Philosophy commanded the attention of great thinkers for a long time.

I do think it raises interesting and important philosophical questions. Just look at all the literature around the Turing test--both supporters and detractors. This has been a fruitful avenue to talk about intelligence even before the advent of gpt.

In your experience does every kind of physical interaction behave the same as every other kind? If I paint a wooden block red and white does it behave like a bar magnet? No. And that's because particular material interactions are responsible for a large magnetic effect.

It would conceivably be possible to have a lot of physical states. That doesn't mean that they are actually possible from our current state and rewrite rules. So it's not actually a given that it can be built just because it's physical.

Your very idea is also predicated on the idea that it's possible for a real object to exist that isn't physical, and I think most modern philosophers reject the idea of a spiritual particle.

It doesn't matter how much like a bar magnet a wooden block painted red and white can be made to look, it will never behave like one.

I get it, but it's not trivial to be precise enough at this point to avoid all false positives and false negatives.

1. Not true. People have been trying to analyze whether mechanical/formal processes can "think" since at least 18th century. E.g. Leibniz wrote:

> if we could find characters or signs appropriate for expressing all our thoughts as definitely and as exactly as arithmetic expresses numbers or geometric analysis expresses lines, we could in all subjects in so far as they are amenable to reasoning accomplish what is done in arithmetic and geometry

2. You're missing the fact that meaning of words is defined through their use. It's an obvious fact that if people call certain phenomenon "thinking" then they call that "thinking".

3. The normal process is to introduce more specific terms and keep more general terms general. E.g. people doing psychometrics were not satisfied with "thinking", so they introduced e.g. "fluid intelligence" and "crystallized intelligence" as different kinds of abilities. They didn't have to redefine what "thinking" means.

Again, people were using words for thousands of years before there were any dictionaries/linguists/academics.

Top-down theory of word definitions is just wrong. People are perfectly capable of using words without any formalities.

LLM output is in no way more effective than human output.

> If the LLM output is more effective than a human at problem solving, which I think we can all agree requires intelligence

Your premise is wrong.

Unless you want to claim that the distant cause by way of the training data is us, but that's exactly the conclusion you're trying to avoid. After all, we put the patterns in the training data, which means we already did the upfront intellectual work for the LLM.

> forming a judgement by a process of logic is precisely what these LLMs do, and we can see that clearly in chain-of-logic LLM processes

I don't know how you arrived at that conclusion. This is no mystery. LLMs work by making statistical predictions, and even the word "prediction" is loaded here. This is not inference. We cannot clearly see it is doing inference, as inference is not observable. What we observe is the product of a process that has a resemblance to the products of human reasoning. Your claim is effectively behaviorist.

> An LLM is for sure using evidence to get to conclusions, however.

Again, the certainty. No, it isn't "for sure". It is neither using evidence nor reasoning, for the reasons I gave. These presuppose intentionality, which is excluded by Turing machines and equivalent models.

> [w.r.t. "analyze"] I have seen LLM do this, precisely according to the definition above.

Again, you have not seen an LLM do this. You have seen an LLM produce output that might resemble this. Analysis likewise presupposes intentionality, because it involves breaking down concepts, and concepts are the very locus of intentionality. Without concepts, you don't get analysis. I cannot understate the centrality of concepts to intelligence. They're more important than inference and indeed presupposed by inference.

> Philosophically I would argue that it's impossible to know what these processes look like in the human mind, and so creating an equivalency (positive or negative) is an exercise in futility.

That's not a philosophical claim. It's a neuroscientific one that insists that the answer must be phrased in neuroscientific terms. Philosophically, we don't even need to know the mechanisms or processes or causes of human intelligence to know that the heart of human intelligence is intentionality. It's implicit in the definition of what intelligence is! If you deny intentionality, you subject yourself to a dizzying array of incoherence, beginning with the self-refuting consequence that you could not be making this argument against intentionality in the first place without intentionality.

> At what point do we say that the distinction between the image of man and man itself is moot?

Whether something is moot depends on the aim. What is your aim? If you aim is theoretical, which is to say the truth for its own sake, and to know whether something is A or something is B and whether A is B, then it is never moot. If your aim is practical and scoped, if you want some instrument that has utility indistinguishable from or superior to that of a human being in the desired effects that it produces, then sure, maybe the question is moot in that case. I don't care if my computer was fabricated by a machine or a human being. I care about the quality of the computer. But then, in the latter case, you're not really asking whether there is a distinction between man and the image of man (which, btw, already makes the distinction that for some reason you want to forget or deny, as the image of a thing is never the same as the thing). So I don't really understand the question. The use of the word "moot" seems like a category mistake here. Besides, the ability to distinguish two things is an epistemic question, not an ontological one.

Humans first start with recognizing the problem, then search through their list of abilities to find the best skill for solving it, thus "autocomplete" their inner shell's commandline, before they start execution, to stay with that picture. Common AIs today are not much different from this, especially with reasoning-modes.

> you're not throwing guesses until something statistically likely to be correct sticks.

What do you mean? That's exactly how many humans are operating with unknown situations/topics. If you don't know, just throw punches and look what works. Of course, not everyone is ignorant enough to be vocal about this in every situation.

> I have to disagree here. When you are tasked with dividing 2 big numbers you most certainly don't "autocomplete" (with the sense of finding the most probable next tokens, which is what an LLM does), rather you go through set of steps you have learned.

Why do you think that this is the part that requires intelligence, rather than a more intuitive process? Because they have had machines that can do this mechanically for well over a hundred years.

There is a whole category of critiques of AI of this type: "Humans don't think this way, they mechanically follow an algorithm/logic", but computers have been able to mechanically follow algorithms and perform logic from the beginning! That isn't thinking!

I'd say, they are all doing the same, just in different domains and level of quality. "Understanding the topic" only means they have specialized, deeper contextualized information. But at the end, that student also just autocompletes their memorized data, with the exception that some of that knowledge might trigger a program they execute to insert the result in their completion.

The actual work is in gaining the knowledge and programs, not in accessing and executing them. And how they operate, on which data, variables, objects, worldview or whatever you call it, this might make a difference in quality and building speed, but not for the process in general.

There are no true and untrue claims about how the brain works, because we have no idea how it works.

The reason people give that humans are not auto-complete is "Obviously I am not an autocomplete"

Meanwhile, people are just a black box process that output words into their head, which they then take credit for, and calling it cognition. We have no idea how that black box that serves up a word when I say "Think of a car brand" works.

Similar, not identical. Like a bicycle and car are both vehicles with tires, but are still not identical vessels.

No, it's more than information retrieval. The LLM is deciding what information needs to be retrieved to make progress and how to retrieve this information. It is making a plan and executing on it. Plan, Do, Check, Act. No human in the loop if it has the required tools and permissions.

> LLMs do a good job of teasing it out that resembles reasoning/thinking but really isn't.

Given the fact that "thinking" still hasn't been defined rigourously, I don't understand how people are so confident in claiming they don't think.

Depends who you ask, what their definition of thinking is.

This is akin to "Show a human an optical illusion that exploits their physiology".

LLM's be like "The dumb humans can't even see the dots"[1]

[1]https://compote.slate.com/images/bdbaa19e-2c8f-435e-95ca-a93...

Ask an illiterate person the same thing and they will fail badly too. Is it impossible to have intelligence without literacy? (Bonus: if so, how was writing invented?)

Now try a different language. My take is hard RL tuning to fix these "gotcha:s" since the underlying model can't do it on its own.

OpenAI is working on ChatGPT the application and ecosystem. They have transitioned from model building to software engineering with RL tuning and integration of various services to solve the problems the model can't do on its own. Make it feel smart rather than be smart.

This means that as soon as you find a problem where you step out of the guided experience you get the raw model again which fails when encountering these "gotchas".

Edit - Here's an example where we see a very tuned RL experience in English where a whole load of context is added on how to solve the problem while the Swedish prompt for the same word fails.

https://imgur.com/a/SlD84Ih

> It does not imply it either.

Right, it's irrelevant to the question of whether they can reason.

> to claim reasoning you need evidence

Frankly I have no idea what most people are talking about when they use the term and say these models can't do it. It seems to be a similarly hand-wavey exercise as when people talk about thinking or understanding.

> it needs to reliably NOT hallucinate results for simple conversations for example (if it has basic reasoning).

That's not something I commonly see in frontier models.

Again this doesn't seem related to reasoning. What we call hallucinations would be seen in something that could reason but had a fallible memory. I remember things incorrectly and I can reason.

> it does not actually take your code and debug it

It talks through the code (which it has not seen) and process step by step, can choose to add logging, run it, go through the logs, change what it thinks is happening and repeat. It can do this until it explains what is happening, creates test cases to show the problem and what triggers it, fixes it and shows the tests pass.

If that's not debugging the code I really don't know what to call it.

You're right. Unfortunately, it seems that not many are willing to admit this and be (rightly) impressed by how remarkably effective LLMs can be, at least for manipulating language.

LLMs are increasingly trained on images for multi-modal learning, so they too would have seen one object, then two.

The instantiation of models in humans is not unsupervised, and language, for instance, absolutely requires labelled data and structured input. The predefined objective is “expand”.

See also: feral children.

Indeed, and it seems like they would really struggle to output coherent text at all if there was not some kind of pre-planning involved (see how even humans struggle with it in games where you have to construct a sentance by having each person shout out one word at a time). Even GPT-2 likely had at least some kind of planning for the next few words in order to be as coherent as it was.

It seems models are pre-planning though:

> How does Claude write rhyming poetry? Consider this ditty:

> He saw a carrot and had to grab it,

> His hunger was like a starving rabbit

> To write the second line, the model had to satisfy two constraints at the same time: the need to rhyme (with "grab it"), and the need to make sense (why did he grab the carrot?). Our guess was that Claude was writing word-by-word without much forethought until the end of the line, where it would make sure to pick a word that rhymes. We therefore expected to see a circuit with parallel paths, one for ensuring the final word made sense, and one for ensuring it rhymes.

> Instead, we found that Claude plans ahead. Before starting the second line, it began "thinking" of potential on-topic words that would rhyme with "grab it". Then, with these plans in mind, it writes a line to end with the planned word.

[https://www.anthropic.com/research/tracing-thoughts-language...]

The part about strawberry is just not right. That problem was solved. And I do think it's a stretch to say German speakers think of the entire sentence before speaking it.

without getting into theory of mind it's a bit difficult to elaborate, and I don't have the time or the will for that. But the short version is that thinking is interconnected with BEING as well as will, and the Agent has neither, in a philosophically formal sense. The agent is deterministically bound. So it is a fancy Rube Goldberg machine that outputs letters in a way that creates the impression of thought, but it is not thought, in the same way that some birds can mimic human speech without even the slightest hint as to the words' or sentences' meaning, underlying grammar, connotations, subtext, context, intended use, likely effect, etc. Is speech speech if the speaker has no concept whatsoever of said speech's content, and can not use it to actualize itself? I'd say no. It's mimicry, but not speech. So that means speech is something more than just its outward aspect - the words. It is the relation of something invisible, some inner experience known only to the speaker, VIA the words.

Whereas a gorilla who learns sign language to communicate and use that communication to achieve aims which have direct correlation with its sense of self - that's thought in the Cogito, Ergo Sum sense of the word.

Thought as commonly concieved by the layman is a sort of isolated phenomenon that is mechanical in nature and can be judged by its outward effects; whereas in the philosophical tradition defining thought is known to be one of the hard questions for its mysterious qualia of being interconnected with will and being as described above.

Guess I gave you the long answer. (though, really, it could be much longer than this.) The Turing Test touches on this distinction between the appearance of thought and actual thought.

The question goes all the way down to metaphysics; some (such as myself) would say that one must be able to define awareness (what some call consciousness - though I think that term is too loaded) before you can define thought. In fact that is at the heart of the western philosophical tradition; and the jury consensus remains elusive after all these thousands of years.

I don't know that most people think about that at all. For me, I have learned not to dismiss the remuninating, reordering, reframing that my brain performs without me deliberately reasoning line by line about it. Limiting my brain to deliberate line by line reasoning would be very limiting and costly.

"Thinking" to me is very much NOT just conscious reasoning. So much of what I think is not done consciously.

Indeed "let me think about it" is often simply giving my brain time to "sit on it", for another expression - only after which will I have enough mind time on the various alternatives for a worthwhile conscious decision.

True, modern Photocopiers are not really Photocopiers any more and just a pc with scanner and printer. Those could be described as "thinking", in the same sense as any computer is thinking. But from my understanding, the original comment was explicitly about a pure copy-device, without any "brain" involved.

That has a logic condition, no?

No, because it is not intentional.

> They're not thinking, it's doing math, mathematical transformations of data

Whatever thinking fundamentally is, it also has an equivalence as a mathematical transformation of data. You're assuming the conclusion by saying that the two mathematical transformations of data are not isomorphic.

A simulation of information processing is still information processing, just like running Windows in a QEMU VM is still running Windows.

The Chinese Room experiment applies equally well to our own brains - in which neuron does the "thinking" reside exactly? Searle's argument has been successfully argued against in many different ways. At the end of the day - you're either a closet dualist like Searle, or if you have a more scientific view and are a physicalist (i.e. brains are made of atoms etc. and brains are sufficient for consciousness / minds) you are in the same situation as the Chinese Room: things broken down into tissues, neurons, molecules, atoms. Which atom knows Chinese?

> But a simulated mind is not a mind. This was already debated years ago with the aid of the Chinese Room thought experiment.

Yes, debated and refuted. There are many well known and accepted rebuttals of the Chinese Room. The Chinese Room as a whole does understand Chinese.

> But a simulated mind is not a mind.

How would the mind know which one it is?

Maybe your mind is being simulated right now.

It's a sign that they are 'reasoning' imperfectly. If they were just giving responses that 'looked like' chess moves, they would be very bad at playing chess.

(And I would hazard a guess that they are a primarily learning chess from the many games that are posted, as opposed to working things out from the rules. Indeed, if you make up a game and tell chatGPT the rules, it tends to be even worse at following them, let alone figuring out optimal play. But again, it will do so significantly better than random chance, so it's doing something with the information you give it, even if it's not doing so very well. I think it's reasonable to call this thinking, or reasoning, but this mostly becomes an argument of semantics. either way they do it significantly better than random chance but still not tremendously well. If your expectation is that they cannot work with anything novel then you're going to be continually surprised, but if your expectation is that they're as good as a human that has 'learned' from all the material its been given, especially material that's in-context and not in the training data, then you're also going to be disappointed.)

Yeah, this is what LLMs might say too, funny enough.

> Generalizing your experience to everyone else's betrays a lack of imagination.

One guy is generalizing from "they don't work for me" to "they don't work for anyone."

The other one is saying "they do work for me, therefore they do work for some people."

Note that the second of these is a logically valid generalization. Note also that it agrees with folks such as Tim Gowers, who work on novel and hard problems.

This is my experience. For rote generation, it's great, saves me from typing out the same boilerplate unit test bootstrap, or refactoring something that exists, etc.

Any time I try to get a novel insight, it flails wildly, and nothing of value comes out. And yes, I am prompting incrementally and building up slowly.

Even people who do actual hard work need a lot of ordinary scaffolding done for them.

A secretary who works for an inventor is still thinking.

Research mathematicians have been finding the tools useful [1][2]. I think those problems are interesting, novel, and hard. The AI might stumble sometimes, but it also produces meaningful, quality results sometimes. For experts working on interesting problems, that is enough to be useful.

[1] https://mathstodon.xyz/@tao/115420236285085121 [2] https://xcancel.com/wtgowers/status/1984340182351634571

Even most humans will stumble on hard problems, that is the reason they are hard in the first place

I'm genuinely curious what you work on that is so "novel" that an LLM doesn't work well on?

I feel like so little is TRUELY novel. Almost everything is built on older concepts and to some degree expertise can be applied or repurposed.

Dude. We don't all work for NASA. Most day to day problems aren't novel. Most jobs aren't novel. Most jobs can't keep a variety of sometimes useful experts on hand. I do my job and I go home and do my hobbies. Anything I can use at work to keep friction down and productivity up is extremely valuable.

Example prompt (paraphrasing and dumbed down, but not a ton): Some users across the country can't get to some fileshares. I know networking, but I'm not on the networking team so I don't have full access to switch, router, and firewall logs/configurations. It looks kind of random, but there must be a root cause, let's find it.

I can't use Python(security team says so) and I don't have access to a Linux box that's joined to the domain and has access the shares.

We are on a Windows domain controller. Write me a PowerShell 5.1 compatible script to be run remotely on devices. Use AD Sites and Services to find groups of random workstations and users at each office and tries to connect to all shares at each other site. Show me progress in the terminal and output an Excel file and Dot file that clearly illustrates successful and failed connections.

---

And it works. Ok, I can see the issue is from certain sites that use x AND y VPN ipsec tunnels to get to particular cloud resources. I give this info to networking and they fix it right away. Problem resolved in less than an hour.

First of all, a couple years ago, I wouldn't have been able to justify writing something like this while an outage is occuring. Could I do it myself? Sure, but I'm going to have to look up the specifics of syntax and certain commands and modules. I don't write PowerShell for a living or fun, but I do need to use it. I am familiar and know how to write it. But I sure as fuck couldn't sit down and spend an hour or two screwing around working on building a goddamn Dot file generator. Yes, years ago I had a whole pile of little utility modules I could use. But that's a far cry from what I can do now to fit the exact situation < 15 minutes while I do other things like pick up the phone, message coworkers, etc.

Secondly, rather than building little custom tools to hook together as I need, I can just ask for the whole thing. I don't need to save any of that stuff anymore and re-figure out what CheckADFSConns(v2).PS1 that I wrote 8 months ago does and how to use it. "Oh, that's not the one, what the did I name that? Where did I put it?"

I work in an environment that is decades old, the company is over 100 years old, I didn't build any of it myself, is not a tech company, and has tons of tech debt and weird shit. AI is insanely useful. For any given problem, there are dozens of different rabbit holes I could go down because of decades of complete system overhaul changes. Today, I can toss a variety of logs at AI and if nothing else, get a sense of direction of why a handful of PCs are rejecting some web certificates. (Combination of a new security policy and their times mismatching the domain controller, because it was new, and NTP wasn't configured properly. I wasn't even looking for timestamps, but it noticed event offsets and pointed it out).

I feel like this community isn't very familiar with what that's like. We aren't all working on self driving cars or whatever seems hard at a brand new company with new everything and no budget. Some of us need to keep the systems running that help people to make actual things. These environments are far from pristine and are held together by underpaid and underappreciated normies through sheer willpower.

Is this kind of work breaking technical frontiers? No. But it's complicated, difficult, and unpredictable. Is it novel? The problems are, sometimes.

Generalizing your experience to everyone else's betrays your lack of self-awareness, sir.

Yes, please this is literally what I want to see. I have yet to see an example where an LLM did anything that was sufficiently difficult. Not saying they can't be useful, but for anything past the basics they are really all over the place. And if we were paying anywhere near the true costs it wouldn't be even worth trying.

See my comment to parent. One example of many. You can say "Oh, well, it just sounds like your company needs better tools and processes, you don't really need AI for any of that. You should just invest in a tool for this and monitor that and have managment prioritize..."

Yeah, I know, yet here we are and it saves me boatloads of time.

Our intelligence, yes. But that doesn't establish it as essential for thought.

> a high chance that our brains require "write access" to function

There are multiple learning mechanisms that happen on different time-frames, eg neural plasticity, hippocampus are both longer-term processes for memory consolidation. Whereas the content of “RAM” might be better modeled as a set of fast dynamic weights representing ions and neurotransmitter concentrations.

My hunch is that you could model the latter fast weights in volatile memory, but I wouldn’t count these as “modifying the structure”.

Do you have any particular systems in mind where you have reason to believe that permanent modification is required for brains to function?

I wonder why we need to sleep so much though

> Start a new session with a blank context

Why would I use a blank context with Claude Code? I have it dump the stuff I want to save in CLAUDE.md and it reloads it in future sessions.

I've certainly got useful and verifiable answers. If you're not sure about something you can always ask it to justify it and then see if the arguments make sense.

Also, does it matter?

The point being made here is about the data LLMs have been trained with. Sure that contains questions&answers but obviously not all of it is in that form. Just like an encyclopedie contains answers without the questions. So imo specifying this as 'no-one asked this before' is irrelevant.

More interesting: did OP get a sensible answer to a question about data which definitely was not in the training set? (and indeed, how was this 'definitely' established'). Not that if the answer is 'yes' that'll prove 'thinking', as opposed to calling it e.g. advanced autocompletion, but it's a much better starting point.

Because I gave them a unique problem I had and it came up with an answer it definitely didn't see in the training data.

Specifically I wanted to know how I could interface two electronic components, one of which is niche, recent, handmade and doesn't have any public documentation so there's no way it could have known about it before.

ChatGPT didn't have any issue when I recently asked something very similar.

https://chatgpt.com/share/6909b7d2-20bc-8011-95b6-8a36f332ac...

I think most people would agree that submarines are swimming.