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

Technical, cognitive, and intent debt

martinfowler.com

Post reply on HN
Print view View original

41–50 of 103 posts

Re: Technical, cognitive, and intent debt

#41

Post by whattheheckheck »

hibikir wrote: post #6

LLMs don't lack the virtue of laziness: it has it if you want it to, by just having a base prompt that matches intent. I've had good success convincing claude backed agents to aim for minimal code changes, make deduplication passes, and basically every other reasonable "instinct" of a very senior dev. It's not knowledge that the models haven't integrated, but one that many don't have on their forefront with default s…

You should go get attention at conferences. You could write a book called

Practical LLM Coding

Re: Technical, cognitive, and intent debt

#42

Post by sally_glance »

awesome_dude wrote: post #20
dc_giant wrote: post #14

Earlier quoted context omitted.

Mind sharing the instructions you give Claude to go for minimal code changes etc?

I often say to Claude "you're doing X when I want Y, how can I get you to follow the Y path without fail" and Claude will respond with "Edit my claude.md to include the following" which I then ask Claude to do.

Not sure this is a great idea. The model only internalized what it was trained on and writing prompts/context for itself isn't part of that. I try to keep my context as clean as possible, mostly today's models seem smart/aligned enough to be steered by a couple of keywords.

Re: Technical, cognitive, and intent debt

#44

Post by meander_water »

Unfortunately large parts of the paper that he linked to from the Wharton school is entirely AI generated, and yet to be peer reviewed.

I realize that most researchers use AI to assist with writing, but when the topic of your paper is "cognitive surrender", I struggle to take any content in there seriously.

Re: Technical, cognitive, and intent debt

#46

Post by __mharrison__ »

marktani wrote: post #16
hibikir wrote: post #6

LLMs don't lack the virtue of laziness: it has it if you want it to, by just having a base prompt that matches intent. I've had good success convincing claude backed agents to aim for minimal code changes, make deduplication passes, and basically every other reasonable "instinct" of a very senior dev. It's not knowledge that the models haven't integrated, but one that many don't have on their forefront with default s…

I agree with your sentiment here. However: > if anything, by most traditional forms of evaluating software quality, the projects I work on are better than what they were 5, 10 years ago, using the same metrics as back then. In this side sentence you're introducing so much vagueness. Can you share insights to get some validation on your claim? What metrics are you using and how is your code from 10, 5, 0 years perform…

My anecdotes for using LLMs to modernize legacy (20-year-old systems):

- 40x speed improvement

- Painless env setup

- 20 Second deploy

- 90+% test coverage

- Ability to quickly refactor

- Documentation

(The original system that I wrote with one other programmer 20 years ago took 1.5+ years to write. Modern rewrite: 2 days)

Re: Technical, cognitive, and intent debt

#47

Post by ai_slop_hater »

meander_water wrote: post #44

Unfortunately large parts of the paper that he linked to from the Wharton school is entirely AI generated, and yet to be peer reviewed. I realize that most researchers use AI to assist with writing, but when the topic of your paper is "cognitive surrender", I struggle to take any content in there seriously.

> I realize that most researchers use AI to assist with writing

This is disgusting

Re: Technical, cognitive, and intent debt

#48

Post by stingraycharles »

ai_slop_hater wrote: post #47
meander_water wrote: post #44

Unfortunately large parts of the paper that he linked to from the Wharton school is entirely AI generated, and yet to be peer reviewed. I realize that most researchers use AI to assist with writing, but when the topic of your paper is "cognitive surrender", I struggle to take any content in there seriously.

> I realize that most researchers use AI to assist with writing This is disgusting

Unfortunately this is the new reality, it’s everywhere.

Re: Technical, cognitive, and intent debt

#49

Post by curio_Pol_curio »

PaulHoule wrote: post #4

Hits the spot for me. I am always pushing back on AI to simplify and improve concision.

How does it --if it does-- relate to your idea of "affordability porn" :)

That line (between your other values?) was uproarious; I apologise for not u*voting it, partially because I couldn't vocalise my peculiar fetish att (+ "gnarliness-pornstar" doesn't sound nearly as enticing as "AI-affordability-pornstar" X)

Re: Technical, cognitive, and intent debt

#50

Post by chrisweekly »

konovalov-nk wrote: post #39

This is my current visualization of the problem: https://excalidraw.com/#json=y1fSSx2z8-0nFs7CDnqhp,d9Di8JdGU... I think the "cognitive bottlenecks" in software engineering live between artifacts, where code is simply one of them. outcome → requirements → spec → acceptance criteria → executable proof → review I'm making experimental tooling that automates the boring parts around those transitions, while keeping human…

cool dataviz but it's editable! trying to pan and zoom and scoll on my phone led to moving elements around on the canvas
Post reply on HN