Talking to LLMs has improved my thinking

https://philipotoole.com/why-talking-to-llms-has-improved-my-thinking/

by otoolep • 6 months ago

186 143 6 months ago

Klaster_13• 6 months ago

This article matches my experience as well. Chatting with LLM has helped me to crystalize ideas I had before and explore relevant topics to widen the understanding. Previously, I wouldn't even know where to begin with when getting curious about something, but ChatGPT can tell you if your ideas have names, if they were explored previously, what primary sources there are. It's like a rabbit hole of exploring the world, a more interconnected one where barriers of entry to knowledge are much lower. It even made me view things I previously thought of as ultra boring in different, more approachable manner - for example, I never liked writing, school essays were a torture, and now I may even consider doing that out of my own will.

snek_case2• 6 months ago

In the early 2000s Wikipedia used to fill that role. Now it's like you have an encyclopedia that you can talk to.

What I'm slightly worried about is that eventually they are going to want to monetize LLMs more and more, and it's not going to be good, because they have the ability to steer the conversation towards trying to get you to buy stuff.

deadbabe• 6 months ago

Enshittification is always inevitable in a capitalist world, but not always easy to predict how it will happen.

idiotsecant• 6 months ago

It's also inevitable that better and better open source models will be distilled as frontier models advance.

pmarreck• 6 months ago

they are going to want to monetize LLMs more and more

Not only can you run reasonably intelligent models on recent relatively powerful PC's "for free", but advances are undoubtedly coming that will increase the efficient use of memory and CPU in these things- this is all still early-days

Also, some of those models are "uncensored"

Klaster_13• 6 months ago

One of the approaches to this that I haven't seen being talked about on HN at all is LLM as public infrastructure by the government. I think EU can pull this off. This also addresses overall alignment and compute-poverty issue. I wouldn't mind if my taxes paid for that instead of a ChatGPT subscription.

resonious• 6 months ago

Right, this is what happened with search engines. And "SEO for LLMs" is already a thing.

attila-lendvai4• 6 months ago

or more generally than just ads: make you believe stuff that makes you act in ways that is detrimental to you, but benefitial to them (whoever sits in the center and can control and shape the LLM).

i.e. the Nudge Unit on steroids...

care must be taken to avoid that.

anon_anon12• 6 months ago

I can envision this as being in the boots of Truman from Truman Show where some advertisement is thrown at your face randomly

michaelbrave• 6 months ago

I sort of already had an experience where it did kinda. I was consulting with it potential fashion choices to upgrade my work uniform, to look professional but still creative, basically to look more like a creative director. It recommended brands, colors, styles etc. Then I was asking about eyeglass frames showed it three pictures, described my facial features and it was like "you have to buy this one now" more enthusiastic than expected. It wasn't ads or anything but there was a bit of salesyness in there.

gradus_ad• 6 months ago

I think the best existing "product" analogy for LLM's is coffee.

Coffee is a universally available, productivity enhancing commodity. There are some varieties certainly, but at the end of the day, a bean is a bean. It will get the job done. Many love it, many need it, but it doesn't really cost all that much. Where people get fancy is in all the fancy but unnecessary accoutrements for the brewing of coffee. Some choose to spend a lot on appliances that let you brew at home rather than relying on some external provider. But the quality is really no different.

Apparently global coffee revenue comes out to around $500B. I would not be surprised if that is around what global AI revenue ends up being in a few years.

normie30003• 6 months ago

Enjoyable analogy.

Some choose to spend a lot on appliances that let you brew at home rather than relying on some external provider.

This makes it sound like buying brewed coffee is the budget option. But the real budget option I've seen is to brew at home. Almost any household will have an appliance to boil water. Then add instant coffee.

I don't understand why, but in my experience instant coffee seems to be the baseline even in coffee-producing countries.

teiferer4• 6 months ago

Coffee is a universally available, productivity enhancing commodity

The analogy carries further than you intended. If you have never reached addiction stage, then there is no factual productivity enhancement. "But I'm so much less productive if I haven't had my morning coffee" Yeah, because you have an addiction. It sounds worse than it is, if you just don't drink coffee for a few days the headaches will subside. But it doesn't actually enhance productivity beyond placebo.

glitchcrab• 6 months ago

But the quality is really no different.

Hard disagree. As someone who is somewhat into the home brewing rabbit hole, I can tell you that the gulf between what I can make at home and what you get in Starbucks is enormous. And I'm no expert in the field by any means.

The rest of your analogy holds up, but not that sentence.

eudamoniac2• 6 months ago

Not the best analogy because coffee has massive quality differences that anyone can tell in a real comparison. Brewing at home is also cheaper and requires nothing more than a $20 French press.

I have personally administered double blind taste tests to four unrelated coffee drinkers who believed their current coffee (Keurig, Nespresso, pre ground) was good. They all thought the actual good coffee was much better in the blind tasting, to the extent that they all permanently stopped drinking their previous coffee. Exclamations of shock occurred.

Coffee is a commodity only out of ignorance. It should be treated as fresh produce of numerous varietals.

Have there been any such "tastings" of LLMs?

afro88• 6 months ago

I'm not great with math beyond high school level. But I am very interested in, among many things, analog synthesiser emulations. The "zero delay filter" was a big innovation in the mid 2000s that led to a big jump in emulation accuracy.

I tried to understand how they work and hit a brick wall. Recently I had a chat with an LLM and it clicked. I understand how the approximation algorithm works that enables solving for the next sample without the feedback paradox of needing to know it's value to complete the calculation.

Just one example of many.

It's similar to sitting down with a human and being able to ask questions that they patiently answer so you can understand the information in the context of what you already know.

This is huge for students if educational institutions can get past the cheating edge of the double edged sword.

attila-lendvai4• 6 months ago

educational institutions became pretty much obsolete with the advent of the internet (i.e. marginalized the cost of the flow of information).

what we need (if anything besides reputation tracking), is (maybe) a separate institution for testing and issuing diplomas... which, BTW, can be trusted more with QA than the very producers themselves.

producers = QA has always been such a contradiction of schools...

fatherwavelet• 6 months ago

audio DSP is a great example. Especially because the proof is in the output if you are then able to make a cool sounding analog filter emulation that you would not have otherwise.

I disagree on the students in educational institutions though. This is the biggest thing for the autodidact who doesn't have the privilege of the educational institution. I think of time, money and effort that would be needed to talk to a professor one on one about analog filter emulation. It is not happening for me.

There are also societal/social high pass filters to even get in the door for these educational institutions. I would just get filtered out anyway. It seems to me in time that entire concept will simply become null and void.

whatever1• 6 months ago

LLM as a rubber duck is a great use case.

NitpickLawyer• 6 months ago

Especially with the great unlock that was made possible by large (usable) context windows. You can now literally "throw the book" at an LLM and get grounded stuff that is at or above what you could do yourself. But it can be done on-demand, on almost every subject there is, at lower and lower cost.

montag• 6 months ago

Wasn’t it George Orwell who said “writing is thinking”?

Klaster_13• 6 months ago

That sounds true when you have already internalized the idea. But my environment never even suggested in can be approached this way. My school didn't teach me how to write, we just had to. Uni didn't explain this either and that was part of the reason why I dropped out. You can't make progress when you don't know what questions to ask and nobody sees your struggles and provides guidance.

ziofill• 6 months ago

Finally I can relate to someone’s experience. For me even playing with image generators has improved my imagination.

slfreference2• 6 months ago

ghosts react : imagine a youtube channel but opinions expressed are from the POV of a ghost.

put the above prompt and enjoy some imaginative writing.

gloflo• 6 months ago

https://m.youtube.com/watch?v=5ZqBunlBtn4

slfreference2• 6 months ago

prompt: Collapse of Circle to 3 points is like Quantum mechanics of mathematics.

hbarka• 6 months ago

I share the sentiment here about LLMs helping to surface personal tacit knowledge and the same time there was a popular post[1] yesterday about cognitive debt when using AI. It's hard not to be in agreement with both ideas.

[1] https://news.ycombinator.com/item?id=46712678

llIIllIIllIIl• 6 months ago

I guess it depends on how people interact with LLM. Cognitive debt may be acquired when people `talk` with machines, asking personal questions, like asking what to answer to the sms from a friend, etc.

It may seem different when people `command` LLMs to do particular actions. At the end, this community, most of all probably, understands that LLM is nothing else than advanced auto-complete with natural language interface instead of Bash.

Write me an essay about birds in my area

Than later will be presented as human’s work compared to

How does this codebase charge customers?

When a person needs to add trials to the existing billing.

The latter will result a deterministic code after (many) prompts that a person will be able to validate for correctness (another question if they will though).

dartharva2• 6 months ago

Of course it has, I doubt this is uncommon.

All my childhood I dreamed of a magic computer that could just tell me straightforward answers to non-straightforward questions like the cartoon one in Courage the Cowardly Dog. Today it's a reality; I can ask my computer any wild question and get a coherent, if not completely correct, answer.

teiferer4• 6 months ago

You are in for a rude awakening when you realize that those answers tend to be subtly to blatently wrong especially when the questions are tricky and non-obvious. Once that blind initial trust is shattered and you stary to question the accuracy of what AI gives you back, you see the BS everywhere.

dartharva2• 6 months ago

Of course due diligence and validation is needed if you intend to use the information for something, but if your aim is just to satisfy your curiosity with questions you don't have anyone else to ask, it's a great medium.

thorum• 6 months ago

I agree that LLMs can be useful companions for thought when used correctly. I don’t agree that LLMs are good at “supplying clean verbal form” of vaguely expressed, half-formed ideas and that this results in clearer thinking.

Most of the time, the LLM’s framing of my idea is more generic and superficial than what I was actually getting at. It looks good, but when you look closer it often misses the point, on some level.

There is a real danger, to the extent you allow yourself to accept the LLM’s version of your idea, that you will lose the originality and uniqueness that made the idea interesting in the first place.

I think the struggle to frame a complex idea and the frustration that you feel when the right framing eludes you, is actually where most of the value is, and the LLM cheat code to skip past this pain is not really a good thing.

spiderfarmer• 6 months ago

LLM’s are tools. A huge differentiator between professionals in any profession is how well they know their tools.

But one of the first things to understand about power tools is to know all the ways in which they can kill you.

nurettin• 6 months ago

I often discuss ideas with peers that I trust to be strong critical thinkers. Putting the idea through their filters of scrutiny quickly exposes vulnerabilities that I'd have to patch on the spot, sometimes revealing weaknesses resulting from bad assumptions.

I started to use LLMs in a similar fashion. It is a different experience. Where a human would deconstruct you for fun, the LLM tries to engage positively by default. Once you tell it to say it the way it is, you get the "honestly, this may fail and here's why".

To my assessment, an LLM is better than being alone in a task and that is the value proposition.

vishnugupta2• 6 months ago

I can somewhat relate to this in the sense that LLMs help me explore different paths of my thought process. The only way to do this earlier was to actually sit down and write it all out and carefully look for gaps. But now the fast feedback loop of LLMs speeds up this process. At times it even shows some path which I hadn't thought of. Or it firms up a direction which I thought only had vague connection.

To take one concrete example, it helped me get a well rounded picture of how British despite having such low footprint in India (at their peak there were about 150K of them) were able to colonise it with 300+ million population.

tommica3• 6 months ago

...sense that LLMs help me explore different paths of my thought process

Are you able to expand on this? I'm really curious to know what you mean by "different paths of though process"

vishnugupta2• 6 months ago

That was a typo, sorry. Meant to write “thought process..”.

Continuing my example…LLM listed out a bunch of reasons such as advanced weapons, organizational structure, etc. I can then explore each of those areas further.

Or when I wanted to understand the raise of regional languages in India. Similar process as before…

My larger point was that LLMs now makes it possible to speed run this research curiosity of mine. This sort of a thing was next to impossible in traditional google/web search world.

Of course we need to fact check and eventually read the actual source.

visarga• 6 months ago

That's my main usage for LLMs, they are usually intellectual sparring partners or researching my ideas to see who came up with them before and how they thought about them. So it's debate and literature research.

jkhdigital4• 6 months ago

I started teaching undergraduate computer science courses a year ago, after ~20 years in various other careers. My campus has relatively low enrollment, but has seen a massive increase in CS majors recently (for reasons I won’t go into) so they are hiring a lot without much instructional support in place. I was basically given zero preparation other than a zip file with the current instructor’s tests and homeworks (which are on paper, btw).

I thought that I would be using LLMs for coding, but it turns out that they have been much more useful as a sounding board for conceptual framing that I’d like to use while teaching. I have strong opinions about good software design, some of them unconventional, and these conversations have been incredibly helpful for turning my vague notions into precise, repeatable explanations for difficult abstractions.

iib• 6 months ago

I found Geoffrey Hinton's hypothesis of LLMs interesting in this regard. They have to compress the world knowledge into a few billion parameters, much denser than the human brain, so they have to be very good at analogies, in order to obtain that compression.

bjt12345• 6 months ago

That's essentially the manifold hypothesis of machine learning, right?

TeMPOraL• 6 months ago

I feel this has causality reversed. I'd say they are good at analogies because they have to compress well, which they do by encoding relationships in stupidly high-dimensional space.

Analogies then could sort of fall out naturally out of this. It might really still be just the simple (yet profound) "King - Man + Woman = Queen" style vector math.

normie30003• 6 months ago

I have strong opinions about good software design, some of them unconventional

I'm jealous of your undergrads - can you share some of the unconventional opinions?

jkhdigital4• 6 months ago

I’m required to teach DSA in Java, so I lay down a couple rules early in the course that prohibit 95% of the nonsense garbage that unconstrained OOP allows. Granted, neither of these rules is original or novel, but they are rarely acknowledged in educational settings:

1. All public methods must implement an interface, no exceptions. 2. The super implementation must be called if overriding a non-abstract method.

The end result of strict adherence to these rules is basically that every feature will look like a GoF design pattern. True creative freedom emerges through constraints, because the only allowable designs are the ones that are proven to be maximally extensible and composable.

jkhdigital4• 6 months ago

Another principle that builds on the other two, and is specifically applicable to Java:

- To the greatest extent possible, base interfaces should define a single abstract method which allows them to be functional and instantiated through lambdas for easy mocking.

- Terminal interfaces (which are intended to be implemented directly by a concrete class) should always provide an abstract decorator implementation that wraps the concrete class for (1) interface isolation that can’t be bypassed by runtime reflection, and (2) decoration as an automatic extension point.

tommica3• 6 months ago

It is mapping a latent structure to language in a way that happens to align with your own internal model.

This is well explained! My experience is something similar - I have a vague notion of something, and I then prompt AI for its "perspective" or explanation to that something, and then me being able to have a sense if its response fits is quite a powerful tool.

libraryofbabel2• 6 months ago

I agree with this. It is an extremely powerful tool when used judiciously. I have always learned and sharpened my ideas best through critical dialog with others. (After two and a half thousand years it may be that we still don't have a better way of teaching than the one Socrates advocated.) But human attention is a scarce resource; even in my job, where I can reasonably ping people for a quick chat or a whiteboard session or fire off some slack messages, I don't want to do that too often. People are busy and you need to pick the right moment and make sure you're getting the most value from their precious time.

No such restriction on LLMs: Opus is available to talk to me day or night and I don't feel bad about sending it half-baked ideas (or about ghosting it half way through the discussion). And LLMs read with an attention to detail that almost no human has the time for; I can't think of anyone who has engaged with my writing quite this closely, with the one exception of my PhD advisor.

LLMs conversations are particularly good for topics outside work where I don't have an easily-available conversational partner at all. Areas of math I want to brush up on. Tricky topics in machine learning outside the scope of what I do in my job. Obscure topics in history or philosophy or aviation. And so on. I've learned so much in the last year this way.

But! It's is an art and it is quite easy to do it badly. You need to prompt the LLM to take a critical stance towards your ideas (in the current world of Opus 4.5 and Gemini 3, sycophancy isn't as much of a problem as it was, but LLMs still can be overly oriented to please). And you need to take a critical stance yourself. Interrogate its answers, and push it to clarify points that aren't obvious. Sometimes you learn something new, sometimes you expose fuzziness in the LLM's description (in which case it will usually give you the concept at a deeper level). Sometimes in the back-and-forth you realize you forgot to give it some critical piece of context, and when you do that it reframes the whole discussion.

I see plenty of examples of people just taking LLM's answers at face value like it's some kind of oracle (and I'm sure the comments here will contain many negative anecdotes like that). You can't do that; you need to engage and try and chip away at its position and come to some synthesis. The nice thing is the LLM won't mind having its ideas rigorously interrogated, which is something humans can be touchy about (though not always, and the most productive human collaborations are usually ones where both people can criticize each other's ideas freely).

For better or for worse, the people who will do best in this world are those with a rigorously critical mindset and an ability to communicate well, especially in writing. (If you're in college, consider throwing in a minor in philosophy or history alongside that CompSci major!) Those were already valuable skills, and they have even more leverage now.

neuroelectron• 6 months ago

it's really easy to tell when it's gaslighting you and wasting your time. Pretty much any time you have to explain something to it it already knows.

Antibabelic• 6 months ago

I'm not sure I agree with this article's idea of what "good thinking" is. To me, good thinking is being able to think logically through a problem, account for detail and nuance, be able to see all the possibilities clearly. Not simply put vague intuitions into words. I do think intuitions are important, but they tend to be only a starting point for an investigation, preferrably an empirical one. While intuitions can be useful, trusting them is the root of all sorts of false ideas about the world. LLMs don't really help you question your intuitions, they'll give you false sense of confidence in them. This would make your thinking worse in my opinion.

zombot• 6 months ago

This is rubber ducking with extra steps and a subscription fee.

kensai2• 6 months ago

It definitely helps with expressing oneself in good "structured English" (or whatever natural language you speak). In my humble opinion, this is exactly the future of programming so it is worth it to invest some time and also learn how natural language processing if functioning.

teiferer4• 6 months ago

Does it? I can blurb whatever grammatical, structural, spelling mess into the LLM input, it still gets what I mean. If I do that with a co-worker, they will be either offended or ask if I'm drunk or both.

Just like omnipresent spell-check got people used to not caring about their correct spelling since a machine always fixes it up for them. It made spelling proficiency worse. We could see a similar trend in how people express themselves if they spend a lot if time with forgiving non-judgemental LLMs.

kensai2• 6 months ago

Your best friend or sibling or partner can possibly understand whatever you mumble without being offended, but it adds to ambiguity and errors or misunderstandings. That's why learning to write in bulletproof structured English decreases this danger. Thankfully, the same is desired for LLMs, even if they can catch most unimportant (spelling) errors.

firefoxd2• 6 months ago

Not to dismiss other people's experience, but thinking improves thinking. People tend to forget that you can ask yourself questions and try to answer them. There is such thing as recursive thinking where you end up with a new thought you didn't have before you started.

Don't dismiss this superpower you have in your own head.

soulofmischief• 6 months ago

Writing improves thinking, and when uses correctly, LLMs can increase the rate at which one writes, journals and refines their thoughts.

fhd2• 6 months ago

Just like how writing helps memorisation. Our brains are efficient, they only do what they have to do. Just like you won't build much muscles from using forklifts.

I've seen multiple cases of... inception. Someone going all in with ChatGPT and what not to create their strategy. When asked _anything_ about it, they defended it as if they came up with it, but could barely reason about it. Almost as if they were convinced it was their idea, but it really wasn't. Weird times.

kranner3• 6 months ago

Agreed; also a kind of recursive placebo tends to happen in my experience:

  10 You recognise your thinking (or some other desirable activity) has improved
  20 You're excited about it
  30 You engage more with the thinking (or other activity)
  40 You get even better results
  50 Even more excitement  
  60 GOTO 30

You definitely don't need LLMs for this.

rand846633• 6 months ago

But you also do not need paper to think, but surely much of modern physics would not have happened without paper or blackboards…

bryanrasmussen• 6 months ago

Kranner: GOTO as used in Thinking considered Beneficial.

jraph2• 6 months ago

See also rubberducking [1]

I've seen people solve their own issues by asking me / telling me about something and finding the solution without me having the time to reply numerous times.

Just articulating your thoughts (and using more of your brain on them by voicing them) helps a lot.

Some talk to themselves out loud and we are starting to realize it actually helps.

[1] https://en.wikipedia.org/wiki/Rubber_duck_debugging

johnfn2• 6 months ago

I'm mystified by this comment. Do people really forget that they can think in their own mind?

jraph2• 6 months ago

— john asked to himself.

ares623• 6 months ago

I think there’s a subset of people who don’t have an inner voice. I assume thinking step by step in their head doesn’t work like most people.

I’m glad LLMs help these people. But I’m not gonna trade society because a subset of people can’t write things down.

firefoxd2• 6 months ago

@grok is this true?

simianwords5• 6 months ago

Don’t be mystified if you lack to curiosity to understand how to use new technology. It’s useful to have something to speak to and get feedback on.

coffeefirst• 6 months ago

It’s as if people are rediscovering that writing is thinking. The chatbot is irrelevant, it works even better with a paper notebook.

john01dav• 6 months ago

In my experience LLMs offer two advantages over private thinking:

1) They have access to a vast array of extremely well indexed knowledge and can tell me about things that I'd never have found before.

2) They are able to respond instantly and engagingly, while working on any topic, which helps fight fatigue, at least for me. I do not know how universal this effect is, but using them often means that I can focus for longer. I can also make them do drudgery, like refactoring 500 functions in mostly the same way that is just a little bit too complicated for deterministic tools to do, which also helps with fatigue.

Ideally, they'd also give you a more unique perspective or push-back when appropriate, but they are yes-men too much right now for that to be the case.

Lastly, I am not arguing to not do private thinking too. My argument is that LLM-involved thinking is useful as its own thing.

Lwerewolf• 6 months ago

Re: "yes men" - critical thinking always helps. I kind of treat their responses like a random written down shower thought - malicious without scrutiny. Same with anything that you haven't gone over properly, really.

The advantages that you listed make them worth it.

peepee1982• 6 months ago

No one is arguing that thinking doesn’t improve thinking. But expressing thoughts precisely by formulating them into the formalized system of the written word adds a layer of metacognition and effort to the thinking process that simply isn’t there when 'just' thinking in your head. It’s a much more rigorous form of thinking with more depth - which improves deeper, more effortful thinking.

libraryofbabel2• 6 months ago

Exactly. As distributed systems legend Leslie Lamport puts it: “Writing is nature’s way of letting you know how sloppy your thinking is.” (He added: “Mathematics is nature’s way of letting you know how sloppy your writing is.”)

I still have a lot of my best ideas in the shower, no paper and pen, no LLM to talk to. But writing them down is the only way to iron out all the ambiguity and sort out what’s really going to work and what isn’t. LLMs are a step up from that because they give you a ready-made critical audience for your writing that can challenge your assumptions and call out gaps and fuzziness (although as I said in my other comment, make sure you tell them to be critical!)

Thinking is great. I love it. And there are advantages to not involving LLMs too early in your process. But it’s just a first step and you need to write your ideas down and submit them to external scrutiny. Best of all for that is another person who you trust to give you a careful and honest reading, but those people are busy and hard to find. LLMs are a reasonable substitute.

sublinear2• 6 months ago

I almost entirely agree with you, but the issue is that the information you currently have might not be enough to get the answers you want through pure deduction. So how do you get more information?

I think chatbots are a very clumsy way to get information. Conversations tend to be unfocused until you, the human, take an interest in something more specific and pursue it. You're still doing all the work.

It's also too easy to believe in the hype and think it's at least better than talking to another person with more limited knowledge. The fact is talking has always sucked. It's slow, but a human is still better because they can deduce in ways LLMs never will. Deduction is not mere pattern matching or correlation. Most key insights are the result of walking a long tight rope of deductions. LLMs are best at summarizing and assisting with search when you don't know where to start.

And so we are still better off reading a book containing properly curated knowledge, thinking about it for a while, and then socializing with other humans.

simianwords5• 6 months ago

No I don’t think humans have some magical metaphysical deduction capability that LLMs lack exclusively.

I have had conversations and while they don’t have the exact attentiveness of a human, they get pretty close. But what they do have an advantage in is being an expert in almost any field.

survirtual• 6 months ago

Recursive self-questioning predates external tools and is already well known. What is new is broad access to a low cost, non retaliatory dialogic interface that removes many social, sexual, and status pressures. LLMs do not make people think. They reduce interpersonal distortions that often interfere with thinking. That reduction in specific social biases (while introducing model encoded priors) is what can materially improve cognition for reflective and exploratory tasks.

Simply, when thinking hits a wall, we can now consult a machine via conversation interface lacking conventional human social biases. That is a new superpower.

keybored• 6 months ago

Unfortunately we do neglect more and more of our own innate talents. Imagine sitting there just thinking, without even a reMarkable to keep notes? Do people even trust their memory beyond their immediate working memory?

bijant• 6 months ago

When I was a kid people told me I needed no Chess Computer - You can play chess in your head, you know ? I really tried, no luck. Got a mediocre device for Christmas, couldn't beat it for a while, couldn't lose against it soon after. Won some tournaments in my age group and beyond. Thought there must be more interesting problems to solve, got degrees in Math, Law and went into politics for a while. Friends from College call on your birthday, invite you to their weddings, they work on problems in medicine, economics, niches of math you've never heard of - you listen, a couple of days later, you wake up from a weird dream and wonder, ask Opus 4.5/Gemini 3.0 deepthink some questions, call them back: "did you try X ?" they tell you, that they always considered you a genius. You feel good about yourself for a moment before you remember that Von Neumann needed no LLMs and that José Raúl Capablanca died over half a decade before Turing wrote down the first algorithm for a Chess Computer. An Email from a client pops up, he isn't gonna pay your bill unless you make one more modification to that CRUD app. You want to eat and get back to work. Can't help but think about Eratosthenes who needed neither glasses nor telescopes to figure out the earths circumference. Would he have marvelled at the achievements of Newton and his successors at NASA or made fun of those nerds that needed polished pieces of glass not only to figure out the mysteries of the Universe but even for basic literacy.

dominicrose• 6 months ago

The way most people think is by talking to each other but writing is a stronger way to think and writing to an LLM or with the help of an LLM has some of the benefits of talking with someone. Also, writing and sketchingon a piece of paper have unique advantages.

isodev• 6 months ago

thinking improves thinking

Indeed, people trying to write prompts for the chatbots and continuously iterating on making their prompts clearer / more effective at conveying their needs is an exercise many haven't done since highschool. Who would've thought that working on your writing and reading proficiency may improve your thinking.

iamkonstantin• 6 months ago

I can imagine for some it's quite a challenge to deviate from short-form shitposting they normally do and formulate thoughts in complete sentences for the LLMs.

anotherevan• 6 months ago

It's also absolute awesome how every person's brain works the same way. It makes it some much more convenient that what works for one person works for every person.

4mitkumar• 6 months ago

This is very interesting because I have been thinking vaguely about a somewhat "opposite" effect. In the sense, talking to LLMs kills my enthusiasm for an idea with other people.

Sometimes, I' get excited by an idea, may be even write a bit about it. Then turn to LLMs to explore it a bit more. An hour later, I feel drained. Like I have explored it from so many angles and nuance that it starts to feel tiresome.

And within that span of couple of hours, the idea goes from "Aha! Let's talk to others about it!" to "Meh.."

EDIT: I do agree with this framing from the article though: "Once an idea is written down, it becomes easier to work with..... This is not new. Writing has always done this for me."

shawn10067• 6 months ago

I've also found that talking through an idea with a language model can sharpen my thinking. It works a bit like rubber duck debugging: by explaining something to an impartial listener, you have to slow down and organise your thoughts, and you often notice gaps you didn't realise were there. The instant follow‑up questions help you explore angles you might not have considered.

my_throwaway232• 6 months ago

Your writing disagree -

"This is not <>. This is how <>."

"When <> or <>, <> is not <>. It is <>."

"That alignment is what produces the sense of recognition. I already had the shape of the idea. The model supplied a clean verbal form."

It's all LLM's. Nobody writes like this.

Lucent• 6 months ago

https://www.pangram.com/history/89da46c7-113e-4a27-8f3f-dbc8...

muchfriction• 6 months ago

I was having a similar odd sense of something being off, then got to

This is not new. Writing has always done this for me. What is different is the speed. I can probe half-formed thoughts, discard bad formulations, and try again without much friction. That encourages a kind of thinking I might have otherwise skipped.

This is a mess. The triple enumeration, twice in a row, right in the middle of a message that warranted a more coherent train of thought. That is, they want to say they already experienced similar gains before from writing as an activity, but the llm conversations are better. Better in what way? Faster, and "less friction". What? What is even the friction in... writing? What made it slow as well, like, are you not writing prompts?

The LLM-ness of the formatting is literally getting in the way of the message. Maybe OOP didn't notice before publishing, but they successfully argued the opposite. Their communication got worse.

my_throwaway232• 6 months ago

Ding ding ding!

Reading, and to some extent editing, is not an active task. In order to become better, at anything, you need to actively do the thing. If you're prompting LLM's, and using whatever they produce, all you'll see any improvement in is... prompting.

fullstackchris• 6 months ago

agree with this article 100%... its those who have no long term programming experience who are likely complaining - the models are just a mirror, a coworker... if you can't accurately describe what you want (with the proper details and patterns you've learned across the years) your going to get generic stuff back

fazgha• 6 months ago

Is not like doing a "semantic search ? I have the feeling that LLMs are great in that topic. For example, I describe a design pattern and LLMs give me the technical name of that design pattern.

CurleighBraces2• 6 months ago

I find talking to LLMs both amazing and frustrating, a computer that can understand my plain text ramblings is incredible, but it's inability to learn is frustrating.

A good example, with junior developers I create thorough specs first and as I saw their skills and reasoning abilities progress my thoroughness drops as my trust in them grows. You just can't do that with LLMs

raffraffraff• 6 months ago

You can write an agent.md file and gradually add to it as you develop the project. The reason junior developers get better is that the context goes from low to high over the time you spend working with them. Yes, "learning".

I've found that maintaining a file that is designed to increase the LLM's awareness of how I want to approach problems, how I build / test / ship code etc, leads to the LLM making fewer annoying assumptions.

Almost all of the annoying assumptions that the LLM makes are "ok, but not how I want it done". I've gotten into the habit of keeping track of these in a file. Like the 10 commandments for LLMs. Now, whenever I'm starting a new context I drop in an agent.md and tell it to read that before starting. Fella like watching Trinity learn how to fly a helicopter before getting into it.

It's still not perfect, but I'm doing waaaay more work now to get annoyed by the LLM's inability to "automatically learn" without my help.

CurleighBraces2• 6 months ago

There's limits to AGENTS.md too, a junior will start to understand the concepts/rationale and design decisions and be able to apply that knowledge to future problems, the LLM will not.

It's way too literally in its thinking.

appsoftware• 6 months ago

I agree with the authors observations here. I think rather than it being purely language related, there's a link to the practice of 'rubber ducking', where when you start to explain your problem to someone else it forces you to step through the problem as you start to explain the context, the steps you've tried and where you're stuck. I think LLMs can be that other person for us sometimes, except that other person has a great broad range of expertise.

ljsprague• 6 months ago

The more I do this, the better I get at noticing what I actually think.

Which reminds me of a quote from E.M Forster: "How do I know what I think until I see what I say?"

cess11• 6 months ago

I wonder if this person reads books.

LowLevelBasket• 6 months ago

This guy is older than I am and writes much worse than I do. Maybe AI 'helps' but the writing of this post is terrible and I was left wondering if he has a learning disability and if AI can help with that

1_08iu• 6 months ago

Writing is ultimately just a communication tool. I think the author communicated their ideas effectively. I don't think that it is necessary or appropriate to speculate whether or not they have a learning disability.

eudamoniac2• 6 months ago

Right. If writing is thinking, the OP's thinking is still muddled. Maybe it has improved, or maybe it hasn't, but I don't think we should take advice about how to improve from one who has failed to improve very much.

iammjm• 6 months ago

I hate to be "that guy", but I think this text was at least partially written by AI:

"This is not a failure. It is how experience operates."

This bit is a clear sign to me, as I am repeatedly irritated by the AI I use that basically almost always defaults to this kind of phrasing each time I ask it something. I even asked it explicitly in my system prompt not to do it

mrvmochi• 6 months ago

I wonder if we've conflated thinking with literacy for too long.

While I'm comfortable with text, I often feel that my brain runs much smoother when I'm talking with colleagues in front of a whiteboard compared to writing alone. It makes me suspect that for centuries, we've filtered out brilliance from people whose brains are effectively wired for auditory or spatial reasoning rather than symbolic serialization. They've been fighting an uphill battle against the pen and the keyboard.

I'm optimistic that LLMs (and multimodal models) will finally provide the missing interfaces for these types of thinkers.

roody15• 6 months ago

It has improved my understanding of emotional dynamics between people. If anything has made me realize may be a bit more on the spectrum that I had realized...

macartain• 6 months ago

It's not that you weren't thinking. It's that you weren't thinking /right/...?

Talking to LLMs has improved my thinking

Related Stories