Talking to LLMs has improved my thinking

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.

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.

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

LLM as a rubber duck is a great use case.

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.

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.

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.

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.

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

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.

> 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.

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.

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.

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.

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.

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

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?

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.

[dead]

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

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.

> 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?

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.

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).

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.

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.

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

> ...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"

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.

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.

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.

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.

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.

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.

Have you been talking to LLMs so much that you've completely adopted their style or did you just tell the AI to write this comment for you?