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

Cognitive Debt: When Velocity Exceeds Comprehension

rockoder.com

Post reply on HN
Print view View original

211–220 of 234 posts

Re: Cognitive Debt: When Velocity Exceeds Comprehension

#211

Post by rvba »

tomhow wrote: post #210
rvba wrote: post #209

Earlier quoted context omitted.

It feels like this article was flagged by users who sell AI stuff, because they dont like its content - so they tried to censorship it with some excuse. This article shows flaws with AI driven development.

Do you think it is LLM-generated or not? And how are you making that assessment?

Why do you switch the subject?

I think you should care more about bad actors potentially brigading HN, instead of asking me random questions if I think if this article was written by AI or not.

For me the article is front page worthy (in fact it had quite a lot of upvotes) as it brought an interesting point of view and an interesting discussion.

I dont care if it wqs written by a human, or maybe rewritten by some tool. Substance over form!

For me it looks that the AI-proponents were unhappy with this article so they mass flagged it. Why they dont like it? Because this article has a heavy anti-AI stance.

Re: Cognitive Debt: When Velocity Exceeds Comprehension

#212

Post by vjvjvjvjghv »

Jensson wrote: post #208
layer8 wrote: post #189

Earlier quoted context omitted.

That means your personal growth has plateaued. ;)

And always thinking your code from a year ago is shit means the code you write right now is also shit, so you never get good.

That's the correct attitude.

Re: Cognitive Debt: When Velocity Exceeds Comprehension

#213

Post by tomhow »

rvba wrote: post #211
tomhow wrote: post #210

Earlier quoted context omitted.

Do you think it is LLM-generated or not? And how are you making that assessment?

Why do you switch the subject? I think you should care more about bad actors potentially brigading HN, instead of asking me random questions if I think if this article was written by AI or not. For me the article is front page worthy (in fact it had quite a lot of upvotes) as it brought an interesting point of view and an interesting discussion. I dont care if it wqs written by a human, or maybe rewritten by some too…

The point is that the topic doesn’t matter, and whether you or I like the content doesn’t matter. The HN community and moderation team have come to a consensus that only original human-authored writing has a place here.

There are only 30 places on the front page, and thousands of submissions each day trying to take one of them. It’s reasonable for the audience to expect that a post that has made it to the front page has had sufficient effort invested in it to be deserving of that place.

Something else I’ve noticed (just today, in part due to this subthread): people are far less inclined to feel negatively towards an LLM-generated article or comment if they agree with it. We need to consciously resist being influenced in this way.

Re: Cognitive Debt: When Velocity Exceeds Comprehension

#215

Post by matsemann »

RealityVoid wrote: post #163
matsemann wrote: post #123

Earlier quoted context omitted.

Learning has always been to write things down. Just reading it seldom sticks.

Absolutely not. Learning has been to experiment with the things until you form a effective mental model of the thing. Writing things does ab-so-luetely nothing except make you feel good in the moment. Just like listening to a lecture without engaging with the subject matter deeper. Writing things down is important for organisational persistence of information but that is something else.

Choosing what to write down is making a mental model, extracting the core and thinking about the subject.

Seems to me you're just a bad note-taker that blindly writes things down, and for some reason decided to use that lack of knowledge in a tirade against me..

Re: Cognitive Debt: When Velocity Exceeds Comprehension

#216

Post by Rexxar »

sesm wrote: post #117
hintymad wrote: post #114

Richard Gabriel wrote a famous essay Worse Is Better ( https://www.dreamsongs.com/WorseIsBetter.html ). The MIT approach vs the New Jersey approach does not necessarily apply to the discussion of the merits of coding agent, but the essay's philosophy seems relevant. AI coding sometimes sacrifices correctness or cleanness for simplicity, but it will win and win big as long as the produced code works per its users' sta…

What definition of simplicity implies that it can be at odds with correctness?

I would say "facility" instead of "simplicity" here.

Re: Cognitive Debt: When Velocity Exceeds Comprehension

#217

Post by generallyjosh »

atmosx wrote: post #173
Belphemur wrote: post #164

Earlier quoted context omitted.

Cheaper and faster retrieval to be added to the context and discoverable by the agent. You need more git commands to find the right commit that contains the context you want (either you the human or the LLM burning too many token and time) than just include the right MD file or use grep with proper keywords. Moreover you could need multiple commits to get the full context, while if you ask the LLM to keep the MD file…

I doubt you can give more context to an LLM from a README file than 500 properly written commits. Or to a human for that matter.

The problem isn't giving MORE context to an agent, it's giving the right context

These things are built for pattern matching, and if you keep their context focused on one pattern, they'll perform much better

You want to avoid dumping in a bunch of data (like a year's worth of git logs) and telling it to sort out what's relevant itself

Better to have pre-processing steps, that find (and maybe summarize) what's relevant, then only bring that into context

You can do that by running your git history through a cheap model, and asking it to extract the relevant bits for the current change. But, that can be overkill and error prone, compared to just maintaining markdown files as you make changes

Re: Cognitive Debt: When Velocity Exceeds Comprehension

#218

Post by enknee1 »

bluegatty wrote: post #143
Klaster_1 wrote: post #84

The article very much resonates with my experience past several months. The project I work on has been steadily growing for years, but the amount of engineers taking care of it stayed same or even declined a bit. Most of features are isolated and left untouched for months unless something comes up. So far, I managed growing scope by relying on tests more and more. Then I switched to exclusively developing against a s…

We don't have the right abstractions in place to support true AI driven work. We replaced ourselves but we don't have the tools to do '1 layer up'.

Nailed it.

We desperately need a new set of abstractions for human- and AI-based knowledge.

I prefer humans-as-a-network of abstractions piloting an organic robot perspective. Sans mathematical framework, this is an unsatisfying claim, I know... But just hear me out.

This allows for extreme complexity between individuals and for language to act as a standard serial com channel with high dimensional abstractions embedded across words - a network of abstractions unto itself. Models of this network are embedded in books and 'live' in oral history.

LLMs, then, are just a much better model of the abstraction networks that span people through language (and often thought).

Notice that they're NOT people. And that we are actively developing network science to accommodate the complexities of inherent in examining both the real world and modeled versions of these networks.

As an example, the tools to layer up can be envisioned as more networks on top of these networks: reasoning and cognitive patterns are captured in recursive transformer-based LLMs. So a metacognative model might actively generate LoRA for each prompt.

Again, much math and research needed. But it's been a very useful set of abstractions this far.

Re: Cognitive Debt: When Velocity Exceeds Comprehension

#220

Post by gusmally »

forgetfreeman wrote: post #32
gusmally wrote: post #15

Earlier quoted context omitted.

With the free time gained from not manually writing code, documentation should be part of the workflow. I should start doing this.

"free time gained" lol in what world is that ever a thing?

I guess we work in very different places!
Post reply on HN