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

What I'm Hearing About Cognitive Debt (So Far)

margaretstorey.com

Post reply on HN
Print view View original

111–120 of 150 posts

Re: What I'm Hearing About Cognitive Debt (So Far)

#111

Post by hogehoge51 »

praptak wrote: post #95
hogehoge51 wrote: post #14

Unfortunately I think Cognitive Debt is the cry of the software craftsperson who thought they were an Engineer. Upon working with the agent subcontractor, the agent factory, the agent part vendor, they approached it as a craft; they found themselves wanting to walk through the offices of the subcontractor reviewing screens, inspect pieces at the factory, and get the internal design for the parts they ordered. It's na…

There is no party capable to take responsibility on the other side of the handover protocol.

Yes, this is the thing - an agent is not a counter party. But it role plays one really well.

You would need the agent to be a processing step owned by someone responsible. But the intelligent part of an agent is what makes it viable as something more than a processing step. What to do with an intelligence that can't take responsibility? Not answering this question leads to cognitive debt.

Re: What I'm Hearing About Cognitive Debt (So Far)

#112

Post by raincole »

Yokohiii wrote: post #76
Aperocky wrote: post #59

Earlier quoted context omitted.

You can use AI to manage cognitive debt, but it doesn't reflect on the sprint board. Across the board, I still see people loving to over design things that can be much simpler. This isn't much changed because of LLM, LLM just allowed them to create the complicated implementations much faster.

If the default mode is that LLMs generate crap code that you have to fix with even more LLMs, then something is fundamentally wrong. In terms of over engineering, I wouldn't be surprised if the human tendency for skeuomorphism (combined with an loss of technical skill) will create even weirder code.

The default mode of the whole startup world is humans generate crap code that you have to fix with even more humans. And it has been like that for at least two decades.

Re: What I'm Hearing About Cognitive Debt (So Far)

#113

Post by scorpioxy »

bonesss wrote: post #109
scorpioxy wrote: post #77

Earlier quoted context omitted.

And if a tool is that difficult to use, how can you tell if the problem is in the tool or the user? There's a large industry built around doing training and certifications in agile methodologies now. If a tool is that difficult to get right, maybe it's just not a good tool to begin with. To be fair, the manifesto and methodology is quite good in theory. But I just have never heard of(or experienced) it working proper…

So the widespread existence of business programs, certification and training heavy, obviously proves every project and business methodology is “bad” and the problem is the tool of “business methodologies”? PRINCE2, for example, is constantly fumbled and misunderstood by immature juniors. They don’t get it, and screw it up. So… what? Haphazard planning and last minute project detonations must replace any effort to avo…

I am not sure how you jumped from what I said to this. I don't believe I claimed that every project and business methodology is bad. I can only speak from my experience and am not confident enough to say how every project and business methodology should or shouldn't work.

I do believe you are helping to make my point though. I am saying that the process may very well be perfection but if entities within "meatspace" cannot use it well and may never be able to use it well then how useful really is it.

Re: What I'm Hearing About Cognitive Debt (So Far)

#114

Post by PeterStuer »

Trying to curb and mitigate 'bad' practice through rigor and diligence is a sound reflex, but history has taught us time and time again it is not the restrained that come out on top, but the single digit percentage of those that threw caution to the wind, got lucky, and survived long enough to be a be to afford dealing with the 'debt' (still don't like that metaphor) in the future.

Re: What I'm Hearing About Cognitive Debt (So Far)

#115

Post by prmph »

Aperocky wrote: post #63
efitz wrote: post #52

There are many projects that should not be built agentically. For things that are appropriate to build with agents, I have come to hold the strong opinion that you need to go all-in. If you built it with an agent, then you fix it with an agent, you debug it with an agent, and you change it with an agent. In that case you should not consider yourself the steward of the source code and worry about “cognitive debt”- it’…

This is correct, but it misses out an important dimension. You can inject philosophy into the agent and ensure that it sticks to it. The LLM will, with sufficient drilling, begrudgingly implement it, most important of which is SIMPLE>COMPLEX on all levels and you have to either manually or agentically continuously monitor this. Alternatively, LLM will use its tiny context window to build a true spaghetti that even it…

> Alternatively, LLM will use its tiny context window to build a true spaghetti that even itself cannot fix any more.

And this is (probably) what is happening to the Claude Code product itself. The harness itself has regressed and is increasingly unstable. I get lots of weird glitches:

- I scroll back in the conversation and keep seeing the the same sections repeated, I am not actually able to see the earlier parts of the conversation because of this.

- The whole CLI UI glitches out such that you can't even make sense of what you are seeing. This is usually fixed by resizing the terminal window

- The previous edit in the conversation history gets lost when I escape it to provide direction

- The CLI sometimes consumes huge amounts of memory (more than 10GB per window, multiplied by the number of windows I'm working in)

- Etc

Re: What I'm Hearing About Cognitive Debt (So Far)

#116

Post by Cthulhu_ »

pizzly wrote: post #17

Cognitive Debt has existed much earlier before LLMs became mainstream. Technical people got good at their jobs and then was promoted to management. After time they lost their technical abilities but if they are a good manager they kept up to date with the technological landscape and used their engineering thinking to ensure that the people below them worked to their optimum efficiency to achieve the companies goals.…

This is true; as smarter people than me have said, software engineering is programming over time, and that time aspect involves individuals knowing less and less of a codebase. But that's what these smart people are advocating, in order to keep code maintainable, you need to stick to some rules, processes, patterns, etc.

Whether you apply those things to other developers or LLMs is a bit moot I think, ultimately neither (or you yourself) can be fully trusted to know and understand the full system.

Re: What I'm Hearing About Cognitive Debt (So Far)

#118

Post by i_think_so »

erikerikson wrote: post #19
unignorant wrote: post #15

Earlier quoted context omitted.

I had the same reaction, but the article is not AI-generated according to pangram, which I've generally found reliable. I wonder if LLM turns of phrase and even thought patterns are creeping into normal human thought.

Or, stay with me here, the LLMs were trained on how we, statistically, write.

When you say "we" you're talking about Twitter, right?

Re: What I'm Hearing About Cognitive Debt (So Far)

#119

Post by i_think_so »

jdw64 wrote: post #67
shiveenp wrote: post #30

Earlier quoted context omitted.

Anytime I see “this is not just x, it’s y” i can almost guarantee with high degree of confidence that slop was used.

As someone from outside the Anglophone cultural sphere, when I first learned to write in English, the kind of writing that AI now often produces was taught to me as “formal" writing. But these days, when I write in that formal style, people sometimes say it sounds like AI. That has been a difficult and frustrating point for me. I still find the subtle difference hard to understand.

I was raised and educated well inside the Anglosphere (USA) and was also taught to write formally in that way.

Do the people who say you sound like AI give you any specifics?

Also, if you don't mind, what was your English education like? I understand that quite a few Americans work in South Korea as teachers but I have no details about how that manifests.

Re: What I'm Hearing About Cognitive Debt (So Far)

#120

Post by srdjanr »

yuye wrote: post #44
Ozzie_osman wrote: post #33

I think the antidote is ownership. Every part of a company or product needs some person or small group that owns it, understands it, and feels ownership over its long-term health. They review or decide what level of review changes to it can take. So much of what makes high-functioning teams work is a sense of ownership and stewardship, and what makes low-functioning teams break is a lack thereof. Someone with pride,…

>I think the antidote is ownership. I've said this before, but people gloss over this fact. >Someone with pride, drive, and a high standard feeling responsible for a particular area or thing. I've also said this before, but AI-glazers just respond with "I think we may just have to let go of pride & kudos and their connection to our identity." Most people who vibecode don't give a shit about their work. Any solution i…

Of course there are examples of software killing or being capable of killing (operating machinery or medical devices), but that doesn't apply to probably 90+% of software
Post reply on HN