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

AI makes the easy part easier and the hard part harder

blundergoat.com

Post reply on HN
Print view View original

91–100 of 382 posts

Re: AI makes the easy part easier and the hard part harder

#91

Post by 8note »

redox99 wrote: post #55
ekidd wrote: post #36

Earlier quoted context omitted.

The wrinkle is that the AI doesn't have a truly global view, and so it slowly degrades even good structure, especially if run without human feedback and review. But you're right that good structure really helps.

AGENTS.md is for that global view.

its still not truly global but that seems like a bit pie in the sky.

people still do useful work without a global view, and there's still a human in the loop witth the same ole amount of global view as they ever had.

Re: AI makes the easy part easier and the hard part harder

#92

Post by echelon »

Avshalom wrote: post #86
socketcluster wrote: post #27

I think AI is just a massive force multiplier. If your codebase has bad foundation and going in the wrong direction with lots of hacks, it will just write code which mirrors the existing style... And you get exactly was OP is suggesting. If however, your code foundations are good and highly consistent and never allow hacks, then the AI will maintain that clean style and it becomes shockingly good; in this case, the p…

When you say multiplier, what kind of number are you talking about. Like what multiple of features shipped that don't require immediate fixes have you experienced.

It's coding at 10-20x speed, but tangibly this is at 1.5-2x the overall productivity. The coding speed up doesn't translate completely to overall velocity yet.

I am beginning to build a high degree of trust in the code Claude emits. I'm having to step in with corrections less and less, and it's single shotting entire modules 500-1k LOC, multiple files touched, without any trouble.

It can understand how frontend API translates to middleware, internal API service calls, and database queries (with a high degree of schema understanding, including joins).

(This is in a Rust/Actix/Sqlx/Typescript/nx monorepo, fwiw.)

Re: AI makes the easy part easier and the hard part harder

#93

Post by cadamsdotcom »

esafak wrote: post #74

> On a personal project, I asked an AI agent to add a test to a specific file. The file was 500 lines before the request and 100 lines after. I asked why it deleted all the other content. It said it didn't. Then it said the file didn't exist before. I showed it the git history and it apologised, said it should have checked whether the file existed first. Ha! Yesterday an agent deleted the plan file after I told it to…

These types of failures are par for the course, until the tools get better. I accept having to undo the odd unruly edit as part of the cost of getting the value.

Much smaller issue when you have version control.

Re: AI makes the easy part easier and the hard part harder

#94

Post by Avshalom »

echelon wrote: post #92
Avshalom wrote: post #86

Earlier quoted context omitted.

When you say multiplier, what kind of number are you talking about. Like what multiple of features shipped that don't require immediate fixes have you experienced.

It's coding at 10-20x speed, but tangibly this is at 1.5-2x the overall productivity. The coding speed up doesn't translate completely to overall velocity yet. I am beginning to build a high degree of trust in the code Claude emits. I'm having to step in with corrections less and less, and it's single shotting entire modules 500-1k LOC, multiple files touched, without any trouble. It can understand how frontend API t…

Okay but again what multiplier of features have you actually shipped.

Re: AI makes the easy part easier and the hard part harder

#95

Post by dwallin »

adithyassekhar wrote: post #64
socketcluster wrote: post #27

I think AI is just a massive force multiplier. If your codebase has bad foundation and going in the wrong direction with lots of hacks, it will just write code which mirrors the existing style... And you get exactly was OP is suggesting. If however, your code foundations are good and highly consistent and never allow hacks, then the AI will maintain that clean style and it becomes shockingly good; in this case, the p…

A tangent, I keep hearing this good base, but I've never seen one, not in the real world. No projects, unless it's only you working on it, only yourself as the client, and is so rigid in it's scope, it's frankly useless, will have this mythical base. Over time the needs change, there's no sticking to the plan. Often it's a change that requires rethinking a major part. What we loathe as tight coupling was just efficie…

A important point though is that llm code generation changes that tradeoff. The time/opportunity cost goes way down while the productivity penalty starts accumulating very fast. Outcomes can diverge very quickly.

Re: AI makes the easy part easier and the hard part harder

#96

Post by minimaxir »

hyperadvanced wrote: post #72
redox99 wrote: post #55

Earlier quoted context omitted.

AGENTS.md is for that global view.

Am I stupid or do these agents regularly not read what’s in the agents.md file?

More recent models are better at reading and obeying constraints in AGENTS.md/CLAUDE.md.

GPT-5.2-Codex did a bad job of obeying my more detailed AGENTS.md files but GPT-5.3-Codex very evidently follows it well.

Re: AI makes the easy part easier and the hard part harder

#97

Post by jascha_eng »

otterley wrote: post #63

If coding was always the “easy part,” what was the point of leetcode grinding for interview preparation?

The hard part of leet code is not the coding but learning to think about problems the correct way.

You can solve leet code problems on the white board with some sketches it has nothing to do with the code itself.

Re: AI makes the easy part easier and the hard part harder

#98

Post by iugtmkbdfil834 »

sdf2erf wrote: post #88
rootusrootus wrote: post #75

Earlier quoted context omitted.

> his use cases for LLMs at the time were summarizing emails in his email client Sounds just like my manager. Though he never has made a proclamation that this meant developers should be 10x as productive or anything along those lines. On the contrary, when I made a joke about LLMs being able to replace managers before they get anywhere near replacing developers, he nearly hyperventilated. Not because he didn't belie…

" we will have replaced a lot of other people first." This is flat out wrong and shows your lack of respect and understanding for other jobs.

Eh. Our understanding is what it has been since early 80s and late 90s, because, in reality, not that much has changed. Oh, sure, technology has moved forward and we no longer print TPS reports in triplicate, but we still have three to four layers of professional checkbox checkers at most big corporates.

And this is just stuff that is mandated by government and not a result of ever evolving bureaucracy.

Re: AI makes the easy part easier and the hard part harder

#99

Post by sarchertech »

bethekidyouwant wrote: post #50
zozbot234 wrote: post #34

Earlier quoted context omitted.

The most credible argument against AI is really the expense involved in querying frontier models. If you want to strengthen the case for AI-assisted coding, try to come up with ways of doing that effectively with a cheap "mini"-class model, or even something that runs locally. "You can spend $20k in tokens and have AI write a full C compiler in a week!" is not a very sensible argument for anything.

How much would it cost to pay developer to do this??

It’s hard to say. The compiler is in a state that isn’t useful for anything at all and it’s 100k lines of code for something that could probably be 10k-20k.

But even assuming it was somehow a useful piece of software that you’d want to pay for, the creator setup a test harness to use gcc as an oracle. So it has an oracle for every possible input and output. Plus there are thousands of C compilers in its training set.

If you are in a position where you are trying to reverse engineer an exact copy of something that already exists (maybe in another language) and you can’t just fork that thing then maybe a better version of this process could be useful. But that’s a very narrow use case.

Re: AI makes the easy part easier and the hard part harder

#100

Post by irishcoffee »

AuthAuth wrote: post #54
zjp wrote: post #24

Earlier quoted context omitted.

I call these "embarrassingly solved problems". There are plenty of examples of emulators on GitHub, therefore emulators exist in the latent spaces of LLMs. You can have them spit one out whenever you want. It's embarrassingly solved. There are no examples of what you tried to do.

Its license washing. The code is great because its already a problem solved by someone else. The AI can spit out the solution with no license and no attribution and somehow its legal. I hope American tech legislation holds that same energy once others start taking American IP and spitting it back out with no license or attribution.

The models need to get burned down and retrained with these considerations baked in.
Post reply on HN