Comment by notepad0x90

> Neither can humans. We also just brute force "autocompletion"

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. Same as with the strawberry example, you're not throwing guesses until something statistically likely to be correct sticks.

humans, and even animals track different "variables" or "entities" and distinct things with meaning and logical properties which they then apply some logical system on those properties to compute various outputs. LLMs see everything as one thing, in case of chat-completion models, they're completing text. in case of image generation, they're completing an image.

Look at it this way, two students get 100% on an exam. One learned the probability of which multiple choice options have the likelihood of being most correct based on how the question is worded, they have no understanding of the topics at hand, and they're not performing any sort of topic-specific reasoning. They're just good at guessing the right option. The second student actually understood the topics, reasoned, calculated and that's how they aced the exam.

I recently read about a 3-4 year old that impressed their teacher by reading perfectly a story book like an adult. it turns out, their parent read it to them so much, they can predict based on page turns and timing the exact words that need to be spoken. The child didn't know what an alphabet, word,etc.. was they just got so good at predicting the next sequence.

That's the difference here.

>>> We also just brute force "autocompletion"

Wouldn't be an A.I. discussion without a bizarre, untrue claim that the human brain works identically.

> We also just brute force "autocompletion" with our learned knowledge and combine it to new parts, which we then add to our learned knowledge to deepen the process

you know this because you're a cognitive scientist right? or because this is the consensus in the field?

>Neither can a toddler nor an animal. The level of ability is irrelevant for evaluating its foundation.

Its foundation of rational logical thought that can't process basic math? Even a toddler understands 2 is more than 1.

>But if you add a feedback loop where it can use tools, investigate external files or processes, and then autocomplete on the results, you get to see something that is (close to) thinking

It's still just information retrieval. You're just dividing it into internal information (the compressed representation of the training data) and external information (web search, API calls to systems, etc). There is a lot of hidden knowledge embedded in language and LLMs do a good job of teasing it out that resembles reasoning/thinking but really isn't.

>>you get to see something that is (close to) thinking.

Isn't that still "not thinking"?

Just ask it how many r's are in strawberry and you will realize there isn't a lot of reasoning going on here, it's just trickery on top of token generators.

Sorry to say, Claude Sonnet 4.5 (with and without extended thinking) has this one solved now. So, not “any” LLM, but maybe some still need work.

I presume they finally got around to training the internal reasoning loop into predicting when it needs to apply answer predictions character-by-character.

—- Transcripts from Claude Sonnet 4.5, initially with extended thinking:

> How many a’s in the phrase “artichokes and aardvarks”? Be sure to check your answer.

> Let me count the letter ‘a’ in “artichokes and aardvarks”: • artichokes: 1 ‘a’ (at the beginning) • and: 1 ‘a’ (at the beginning) • aardvarks: 3 ‘a’s (two at the beginning: “aa”, and one in the middle: “ardvarks”) Total: 1 + 1 + 3 = 5 ‘a’s Let me verify by marking them: artichokes and aardvarks Yes, there are 5 letter ‘a’s in the phrase “artichokes and aardvarks”.

> Are you sure that’s correct?

> Let me recount more carefully: “artichokes and aardvarks” Going through each word letter by letter: 1. artichokes - has 1 ‘a’ (first letter) 2. and - has 1 ‘a’ (first letter) 3. aardvarks - has 3 ‘a’s (first letter, second letter, and one more in the middle) Total: 1 + 1 + 3 = 5 ‘a’s Yes, I’m confident the answer is 5. Is there something specific you’d like me to recheck?

> How many r’s in strawberry?

> Let me count the letter ‘r’ in “strawberry”: s-t-r-a-w-b-e-r-r-y Going through each letter: • s: not an r • t: not an r • r: 1st r • a: not an r • w: not an r • b: not an r • e: not an r • r: 2nd r • r: 3rd r • y: not an r There are 3 r’s in “strawberry”.

<Without extended thinking> > How many u’s in universalulis?

> Looking at “universalulis” letter by letter: u-n-i-v-e-r-s-a-l-u-l-i-s There are 2 u’s in “universalulis”.

For what it's worth, when I ask ChatGPT 5, it gets the correct answer every time. The response varies, but the answer is always three.

> This does not preclude reasoning.

It does not imply it either. to claim reasoning you need evidence. it needs to reliably NOT hallucinate results for simple conversations for example (if it has basic reasoning).

> Because I see them solve real debugging problems talking through the impact of code changes or lines all the time to find non-obvious errors with ordering and timing conditions on code they’ve never seen before.

Programming languages and how programs work are extensively and abundantly documented, solutions to problems and how to approach them,etc.. have been documented on the internet extensively. It takes all of that data and it completes the right text by taking the most correct path way based on your input. it does not actually take your code and debug it. it is the sheer volume of data it uses and the computational resources behind it that are making it hard to wrap your head around the difference between guessing and understanding. You too can look at enough stack overflow and (poorly) guess answers for questions without understanding anything about the topic and if you guess enough you'll get some right. LLMs are just optimized to get the amount of correct responses to be high.

And because ALL the marketing AND UX around LLMs is precisely trying to imply that they are thinking. It's not just the challenge of grasping the ridiculous amount of resources poured in, which does including training sets, it's because actual people are PAID to convince everybody those tools are actually thinking. The prompt is a chatbox, the "..." are there like a chat with a human, the "thinking" word is used, the "reasoning" word is used, "hallucination" is used, etc.

All marketing.

> Any thinking that happens with words is fundamentally no different from what LLMs do.

This is such a wildly simplified and naive claim. "Thinking with words" happens inside a brain, not inside a silicon circuit with artificial neurons bolted in place. The brain is plastic, it is never the same from one moment to the next. It does not require structured input, labeled data, or predefined objectives in order to learn "thinking with words." The brain performs continuous, unsupervised learning from chaotic sensory input to do what it does. Its complexity and efficiency are orders of magnitude beyond that of LLM inference. Current models barely scratch the surface of that level of complexity and efficiency.

> Do you have a concept of one-ness, or two-ness, beyond symbolic assignment?

Obviously we do. The human brain's idea of "one-ness" or "two-ness" is grounded in sensory experience — seeing one object, then two, and abstracting the difference. That grounding gives meaning to the symbol, something LLMs don't have.

We do a lot of autocompletion and LLMs overlap with that for sure. I don't know about the "vast majority" even basic operations like making sure we're breathing or have the right hormones prompted are not guesses but deterministic algorithmic ops. Things like object recognition and speech might qualify as autocompletion. But let's say you need to setup health-monitoring for an application. that's not an autocomplete operation. you must evaluate various options, have opinions on it, weigh priorities,etc.. in other words, we do autocompletion but even then the autocompletion is a basic building block or tool we use in constructing more complex decision logic.

If you train an animal to type the right keys on a keyboard that generates a hello world program, you didn't just teach them how to code. they just memorized the right keys that lead to their reward. a human programmer understands the components of the code, the intent and expectations behind it, and can reason about how changes would affect outcomes. the animal just knows how the reward can be obtained most reliably.

I think (hah) you're understimating what goes on when living things (even small animals) think. We use auto-compleition for some tasks, but it is a component of what we do.

Let's say your visual system auto-completes some pattern and detects a snake while you're walking, that part is auto-completion. You will probably react by freezing or panicing, that part is not auto-compleition, it is a deterministic algorithm. But then you process the detected object, auto-compleiting again to identify it as just a long cucumber. But again, the classification part is auto-completion. What will you do next? "Hmm, free cucumber, i can cook with it for a meal" and you pick it up. auto-completion is all over that simple decision, but you're using results of auto-completion to derive association (food), check your hunger level (not auto-completion), determine that the food is desirable and safe to eat (some auto-compleition), evalute what other options you have for food (evaluate auto-complete outputs), and then instruct your nervous system to pick it up.

We use auto-compleition all the time as an input, we don't reason using auto-compleition in other words. You can argue that if all your input is from auto-completion (it isn't) then it makes no difference. But we have deterministic reasoning logical systems that evaluate auto-completion outputs. if your cucumber detection identified it as rotten cucumber, then decision that it is not safe to eat is not done by auto-completion but a reasoning logic that is using auto-completion output. You can approximate the level of rot but once you recognize it as rotten, you make decision based on that information. You're not approximating a decision, you're evaluating a simple logic of: if(safe()){eat();}.

Now amp that up to solving very complex problems. what experiments will you run, what theories will you develop, what R&D is required for a solution,etc.. these too are not auto-completions. an LLM would auto complete these and might arrive at the same conclusion most of the time. but our brains are following algorithms we developed and learned over time where an LLM is just expanding on auto-completion but with a lot more data. In contrast, our brains are not trained on all the knowledge available on the public internet, we retain a tiny miniscule of that. we can arrive at similar conclusions as the LLM because we are reasoning and following algorithms matured and perfected over time.

The big take away should be that, as powerful as LLMs are now, if they could reason like we do, they'd dominate us and become unstoppable. Because their auto-completion is many magnitudes better than ours, if they can write new and original code based on an understanding of problem solving algorithms, that would be gen ai.

We can not just add 1 + 1 but prove that the addition operation is correct mathematically. and understand that when you add to a set one more object, the addition operation always increments. We don't approximate that, we always, every single time , increment because we are following an algorithm instead of choosing the most likely correct answer.

A long time ago I noticed that I sometimes already had a complete thought before my inner monologue turned it into words. A few times I tried skipping the inner monologue because I'd clearly already thought the thought. Turns out the bit of my brain that creates the inner monologue from the thought, can generate a sense of annoyance that the rest of my brain can feel.

Not that it matters, there's evidence that while LLMs output one word at a time, they've got forward-planning going on, having an idea of the end of a sentence before they get there.

Tell that to German-speakers, where the verb comes last, and the order of things in sentences is not anything like English, therefore requiring you to think of the entire sentence before you just spit it out. Even the numbers are backwards (twenty-two is two-and-twenty) which requires thinking.

Furthermore, when you ask an LLM to count how many r's are in the word strawberry, it will give you a random answer, "think" about it, and give you another random answer. And I guarantee you out of 3 attempts, including reasoning, it will flip-flop between right and wrong, but unlike a human, it will be random, because, unlike humans who, when asked "how many r's are in the word strawberry" will not be able to tell you the correct answer every. fucking. time.

edit: formatting