Why thinking out loud with someone beats thinking alone

Some of the value I get coding with LLMs is like that. Like I am working on some code that I 80% understand and going back and forth I get to 100%.

It's simpler than this. Explaining a question/issue to someone involves going back to basics and covering all the foundational info that a third party would not have. When thinking alone, you gloss over this, and may not realize that a foundational assumption is incorrect. When you are forced to explain every step explicitly, these errors or gaps can become apparent without any intervention by the listener.

I have my younger kid explain each math problem to me before she submits it on Khan Academy. My older kid thinks in her head how she would explain a problem before turning in a test. It's a good habit to form.

This proves nothing but, in my earlier days, I'd come home with something on my mind from work and tell my wife about how I couldn't get something to work the way I wanted. She had no clue what I was talking about but she'd offer up clues and suggestions to which I would try to explain to her how things actually worked.

Somewhere in that process it would lead to a solution that I would bring to work the next day!

I don't think the out loud or someone listening / reacting matters at all here. Suspect it's entirely this:

>The thought that was comfortable as a vague impression has to become a sentence, and sentences have structure.

It's not unlike what people like PG say about writing improving thinking...it's the being forced to go from fuzzy directional notions to something you can put on paper in that will stand up to critique.

Same with rubber duck debugging. The verbal part means you need to articulate it clearly but it's not the speaking that helps. Same with writing a detailed spec/prompt for an LLM - I know if its too fuzzy ("set an appropriate timeout") the LLM will spin it's wheels so it forces clarity.

Also suspect that a big part of who we consider intelligent is linked to this. Maybe their internal monologue is just more crisp - closer to what they'd tell a rubber duck.

  I don't think the out loud or someone listening / reacting matters at all here. Suspect it's entirely this:

  >The thought that was comfortable as a vague impression has to become a sentence, and sentences have structure.

In 2017 LLMs weren't powerful enough to generate working code on their own, but my goal was to at least create a chatbot that could help you rubber-duck-debug your way to a solution. Unfortunately the tech wasn't quite strong enough for that, and not enough engineers even knew what rubber-duck-debugging was. RIP Duckly.

Trying to train an LLM on two 1080ti's on the StackOverflow corpus in my living room was a vibe though. Good times.

OMG - strong vibes to Einstein crediting Michele Besso, his colleague at the Swiss Patent Office, with helping him discussing some concepts in the special relativity paper: see at the end of the paper https://www.fourmilab.ch/etexts/einstein/specrel/specrel.pdf

This is so true!

1. Talking or writing requires thoughts to be sequenced so they come out in a way someone can follow

Thinking in your head won’t organize your thought.

2. Talking or writing to someone invites feedback and forces you to make sense, fit in socially etc.

Chatting with an AI or writing in your diary won’t refine or improve your thoughts.

I started my web dev career in 1999 so my main code references were a combination of O’reilly and “for dummies” books. As a wet behind the ears engineer I’d find myself regularly walking over to my more senior friend Dan’s cubicle for help.

Half the time on the walk over, trying to frame the question in my mind I’d figure out the answer or at least next step. It got to the point where Dan would see me heading towards him and suddenly turn around and he’d as “Figure it out?” And I’d throw him a thumbs up on the way back to my desk.

This makes sense when you think about the divided state of the USA today. People were isolated during COVID and had no feedback on opinions formed then. When they started creating bubbles after lockdown, they wanted validation for the opinions they formed without that feedback. Now, people constantly argue online because that feedback they needed while cementing those ideas wasn't there and we aren't willing to take that communication feedback to tweak our opinions based on common sense because we all believe we are right. This article makes a lot of sense.

Communicating ideas helps, but thinking out loud may not work better to some people.

Thinking silently fits Asian Americans better than Euro Americans*.

https://www.psychologytoday.com/us/blog/sex-murder-and-the-m...

Furthermore, it helps to talk with people who think differently from you.

Maybe they studied the same subject but at a different school, or maybe they specialize in something else entirely.

Maybe their first language is different from yours, since language idioms can affect the way we frame problems.

Maybe they want to get into the field you're working on, and your thinking can also be teaching.

For me, this is a big part of the value of a hackerspace/makerspace. The tools are nice, but the intellectual environment is amazing.

Everyone inherently knows this, that's why they reach out to others when stuck on a bug (see also rubber-ducking). But why is it so hard to convince individuals and organizations of the benefits of pair programming?

I wonder if there's a difference between people who have a strong inner voice and those with no inner voice (Anendophasia). I.e. do people w Anendophasia do better on their own than those with a strong inner voice?

Writing is as good, or even better https://www.paulgraham.com/words.html

> The Enigma of Reason (Hugo Mercier and Dan Sperber, 2017): their argumentative theory holds that reasoning evolved for social rather than individual epistemic purposes, to produce and evaluate arguments in group contexts.

Yes! I love that someone wrote this down!

This seems so obvious to me now. I often ask LLMs to cite their sources (they do hallucinate from time to time), and they often give me sources that don't say what is claimed. "How would the LLM know not to give this to me?" I wonder. They're trained to explain but not to convince, so they don't know what's convincing, and they should.

I think humans hallucinate at least as much as LLMs—arguments of any complexity are impossible to formulate without leaping at least a bit—but other humans ground us. That's why when people become socially isolated, they join cults or adopt conspiracy theories or the like.

Conversely, "this is convincing to an expert" converges on “this is true" as our collective expertise grows over time. This is the foundation of the scientific method, of progress in all engineering disciplines, etc.

LLMs are really good rubber ducks.

See also https://en.wikipedia.org/wiki/Rubber_duck_debugging

A collection of thoughts on this.

Pierces Firstness is exactly what drives this.

The move from thinking to semantic conversion is important for investigation/introspection.

Arguing with yourself also seems to engage your brains "theory of mind" centers, so different pathways get activated to examine the problem space.

The problem with Ai is the fact that it hallucinates and if you're doing anything truly novel in an integration or framing sense it bottoms out very quickly and can't engage. A human operator can decompose the problem and get accuracy checks for known areas in the training data of course.

Now to be I'm not saying Ai can't produce novel work on the edge but in my experience it is antagonistic towards those goals.

Case in point, CRDTs, many don't use tombstones but they are the minority, and if you try iterate a new CRDT off of one that doesn't use tombstones, let's say diamond-types, it will keep pulling you back to tombstones.

The problem is that the number of humans who understand dynamic investigation and the push pull of exploring an idea you don't hold with someone has always been very small, and now with reflexive internet argument culture driving how we view "debate" and "discussion".

I don't know if we've reduced the leisure to think or what but things are not great for finding speculative thinking partners.

[dead]