Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Engineering for Bounded Cognition

shapeofthesystem.com

Post reply on HN
Print view View original

31–40 of 42 posts

Re: Engineering for Bounded Cognition

#31

Post by codewithcheese »

supermatt wrote: post #25
dcre wrote: post #16

This reads to me as fully written by LLMs. Pangram agrees. Note the (alleged) author misHQ’s comments on this thread are getting downvoted as obvious slop. https://news.ycombinator.com/item?id=48706307 Even if it were written by hand, it’s a very poor and frankly stupid essay about an interesting topic. “The model's attention is a fixed quantity, and it has to add up to one, so the more things you make it look at, th…

Alleged author here - on my regular account. Thanks for the feedback. I have been quite upfront about the use of AI in the foreword. I have severe inattentive ADHD and have used AI to take my writings and present them in a way in which I feel are much more coherent overall. The actual criticisms you have about the content however, I'd like to challenge: The "adding up to one" is just a simplified gloss over softmax.…

> You have merged the 2 things the post keeps apart - capacity and attention over it.

Maybe you just write like an LLM.

Re: Engineering for Bounded Cognition

#32

Post by supermatt »

codewithcheese wrote: post #31
supermatt wrote: post #25

Earlier quoted context omitted.

Alleged author here - on my regular account. Thanks for the feedback. I have been quite upfront about the use of AI in the foreword. I have severe inattentive ADHD and have used AI to take my writings and present them in a way in which I feel are much more coherent overall. The actual criticisms you have about the content however, I'd like to challenge: The "adding up to one" is just a simplified gloss over softmax.…

> You have merged the 2 things the post keeps apart - capacity and attention over it. Maybe you just write like an LLM.

You’re absolutely right! ;) Honestly - there has been so much human-in-the-loop I wouldn't be surprised if the fine-tuning went both ways.

Re: Engineering for Bounded Cognition

#33

Post by chrisjj »

c3z_ wrote: post #6

I've learned that for both humans and models: system > willpower. The key is entirely in designing the environment. For me personally, that means setting up 'attention getters' for the important things in life - 'totems' that force a context switch. For AI agents, it means well-designed CLI tools that help the agent orient itself in a task and pull exactly the 'context-for-the-job' it needs right then. This is exactl…

> You now have to account for the unknown cognitive construct of a completely different intelligence.

But your LLM training corpus covered that, right? /i

Re: Engineering for Bounded Cognition

#34

Post by supermatt »

geetee wrote: post #30
supermatt wrote: post #25

Earlier quoted context omitted.

Alleged author here - on my regular account. Thanks for the feedback. I have been quite upfront about the use of AI in the foreword. I have severe inattentive ADHD and have used AI to take my writings and present them in a way in which I feel are much more coherent overall. The actual criticisms you have about the content however, I'd like to challenge: The "adding up to one" is just a simplified gloss over softmax.…

I think the problem with "AI assisted" is that it triggers the same alarm bells as AI slop, justified or not, so many readers just turn off. I personally rather read "shitty" writing than AI assisted writing.

It’s a fair criticism. Maybe I should have both: my source and the tidied version. Kind of like the light/dark mode toggle but for shit/slop!

Re: Engineering for Bounded Cognition

#35

Post by konovalov-nk »

I've been thinking about this as well.

To me this is optimization problem. How can we solve a problem if we don't understand it? Understanding takes a lot of effort exactly because our minds are wandering through useless context all the time, and not to mention interruption.

I formulate this problem as:

> Optimize for understanding

I know how to approach solving this exact problem. In fact, I've been doing exactly this since March 2026. We need to figure out how to isolate problems and context around them. And so my best bet right now is using graphs. Links can be easily added or removed between two nodes. And context is simply a group of links and/or linked nodes.

Now. What exactly is "understanding"?

To me, this is process when we look at some unpredictable, chaotic system and then creating structure from it. The chaotic system is an entangled, spaghetti-like graph. The ordered one is one we [hopefully] have in our brains, which allows us to act on it. I don't want to repeat entire article I wrote about this so if you want you can find it on my recent project (it's not ready for HN prime-time yet but I'll post demo soon).

But tl;dr we have "chaotic/unknown graph" and "structured/understood graph", and the bottleneck is moving nodes and links between these two.

The faster we understand the world around us, the better we understand why problems appear, and how to fix them. And once I realized this, to me it became clear where we need to move forward: to connect everything together in a way that makes understanding quick.

And fun fact, I already did this: I connected my article to yours.

Re: Engineering for Bounded Cognition

#36

Post by senkora »

senkora wrote: post #29
james_ross wrote: post #3

[dead]

> which TBH is so dry I'm not sure anyone I've recommended it to has actually finished it :) Challenge accepted!

Done. That was quite interesting, although I see what you mean. I did skip over some of the sections about how to teach concept maps to elementary school students and some of the examples given.

I think my conclusion is that he's probably right that producing and discussing concept maps is the fastest way to share and validate conceptual understanding, so I'll add them to my toolkit.

I'd never heard of the Gowin's Vee chart before (the other main topic of the book) and it seems useful although I can't realistically see a situation where I'd personally use it. There are quite a few similar "planning process" or "research process" systems that cover similar ground. I do like how this one is relatively "zoomed out" to make sure first-and-foremost that your investigation is actually answering some meaningful question within your wider cognitive context.

Re: Engineering for Bounded Cognition

#37

Post by supermatt »

konovalov-nk wrote: post #35

I've been thinking about this as well. To me this is optimization problem. How can we solve a problem if we don't understand it? Understanding takes a lot of effort exactly because our minds are wandering through useless context all the time, and not to mention interruption. I formulate this problem as: > Optimize for understanding I know how to approach solving this exact problem. In fact, I've been doing exactly th…

That’s great! But don’t fall into the trap that the graph is the ultimate representation of all. You will get a topology, but you often need more than topologies to understand the whole. Behaviour of the parts themselves is covered in the manifesto, and there is a companion that covers the connecting of the parts: https://shapeofthesystem.com/the-shape-of-the-whole

Re: Engineering for Bounded Cognition

#38

Post by james_ross »

senkora wrote: post #36
senkora wrote: post #29

Earlier quoted context omitted.

> which TBH is so dry I'm not sure anyone I've recommended it to has actually finished it :) Challenge accepted!

Done. That was quite interesting, although I see what you mean. I did skip over some of the sections about how to teach concept maps to elementary school students and some of the examples given. I think my conclusion is that he's probably right that producing and discussing concept maps is the fastest way to share and validate conceptual understanding, so I'll add them to my toolkit. I'd never heard of the Gowin's Ve…

Ha — you actually did it. Genuinely made my day; you've now read it more recently than I have. And I think you've landed where I did: the concept-mapping part is the keeper and the rest I have not put to practical use.

Re: Engineering for Bounded Cognition

#39

Post by zby »

misHQ wrote: post #7
zby wrote: post #2

It is interesting to compare this to LLMs - they also have the bounded context that you can see as the analogue to our working memory. It can contain enormously more bits of information than the 4 things the article says is the capacity of our working memory - but the 4 things can probably be much more complex internally - they are more like 4 pointers probably. But at some level context engineering is very similar t…

Hello, author here. Lovely comment, and yes: not just similar, but exactly what the article talks about. In the middle. Where it unironically talks about being lost in the middle. And it seems to have made its own point, on even the careful reader!

Frankly I just skimmed that article, and still commented, bad me.

I was also confused by the tag menu - I thought they are sections in the article - I completely failed here :(

By the way I have a page with some more sources for the context degradation phenomenon: https://zby.github.io/commonplace/notes/agent-context-is-con...

Re: Engineering for Bounded Cognition

#40

Post by bossyTeacher »

c3z_ wrote: post #6

I've learned that for both humans and models: system > willpower. The key is entirely in designing the environment. For me personally, that means setting up 'attention getters' for the important things in life - 'totems' that force a context switch. For AI agents, it means well-designed CLI tools that help the agent orient itself in a task and pull exactly the 'context-for-the-job' it needs right then. This is exactl…

> I've learned that for both humans and models: system > willpower. The key is entirely in designing the environment.

Tons of self-help books could be summarized in those 2 lines.

Post reply on HN