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

71–80 of 382 posts

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

#71

Post by swordsith »

kfarr wrote: post #18

I think it makes the annoying part less annoying? Also re: "I spent longer arguing with the agent and recovering the file than I would have spent writing the test myself." In my humble experience arguing with an LLM is a waste of time, and no-one should be spending time recovering files. Just do small changes one at a time, commit when you get something working, and discard your changes and try again if it doesn't. I…

Anyone not using version control or a IDE that will keep previous versions for a easy jump back is just being silly. If you're going to play with a kid who has a gun, wear your plates.

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

#72

Post by hyperadvanced »

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.

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

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

#73

Post by redox99 »

isodev wrote: post #61
redox99 wrote: post #55

Earlier quoted context omitted.

AGENTS.md is for that global view.

That’s not what Claude and Codex put there when you ask them to init it. Also, the global view is most definitely bigger than their tiny, loremipsum-on-steroids, context so what do you do then?

You know you can put anything there, not just what they init, right? And you can reference other doc files.

I should probably stop commenting on AI posts because when I try to help others get the most out of agents I usually just get down voted like now. People want to hate on AI, not learn how to use it.

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

#74

Post by esafak »

> 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 "forget about it" (as in, leave it alone).

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

#75

Post by rootusrootus »

iugtmkbdfil834 wrote: post #58

Some time back, my manager at the time, who shall remain nameless told the group that having AI is like having 10 people work for you ( he actually had a slightly smaller number, but it was said almost word for word like in the article ) with the expectation being set as: 'you should now be able to do 10x as much'. Needless to say, he was wrong and gently corrected over the course of time. In his defense, his use cas…

> 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 believe me, but because he did, and already been thinking that exact thought.

My conclusion so far is that if we get LLMs capable of replacing developers, then by extension we will have replaced a lot of other people first. And when people make jokes like "should have gone into a trade, can't replace that with AI" I think they should be a little more introspective; all the people who aspired to be developers but got kicked out by LLMs will be perfectly able to pivot to trades, and the barrier to entry is low. AI is going to be disruptive across the board.

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

#76

Post by redox99 »

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?

Each agent uses a different file, like claude.md etc (maybe you already knew that).

And it requires a bit of prompt engineering like using caps for some stuff (ALWAYS), etc.

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

#77

Post by dustingetz »

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…

how do you know there is such thing as good code foundations, and how do you know you have it? this is an argument from ego

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

#78

Post by hyperadvanced »

kfarr wrote: post #18

I think it makes the annoying part less annoying? Also re: "I spent longer arguing with the agent and recovering the file than I would have spent writing the test myself." In my humble experience arguing with an LLM is a waste of time, and no-one should be spending time recovering files. Just do small changes one at a time, commit when you get something working, and discard your changes and try again if it doesn't. I…

I don’t think it’s “just” that easy. AI can be great at generating unit tests but it can and will also frequently silently hack said tests to make them pass rather than using them as good indicators of what the program is supposed to be doing.

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

#79

Post by ThrowawayR2 »

seanmcdirmid wrote: post #45
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.

Because hardware costs never goes down and energy efficiency never go up overtime? Whatever the value/$ is now, do you really think it is going to be constant?

If hardware industry news is any indication, hardware costs aren't going to be going down for GPUs, RAM, or much of anything over the next 3-5 years.

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

#80

Post by zozbot234 »

rockinghigh wrote: post #67
anoncow wrote: post #31

Earlier quoted context omitted.

I tried to vibe code a technical not so popular niche and failed. Then I broke down the problem as much as I could and presented the problem in clearer terms and Gemini provided working code in just a few attempts. I know this is an anecdote, but try to break down the problem you have in simpler terms and it may work. Niche industry specific frameworks are a little difficult to work with in vibe code mode. But if you…

It's called problem decomposition and agentic coding systems do some of this by themselves now: generate a plan, break the tasks into subgoals, implement first subgoal, test if it works, continue.

That's nice if it works, but why not look at the plan yourself before you let the AI have its go at it? Especially for more complex work where fiddly details can be highly relevant. AI is no good at dealing with fiddly.
Post reply on HN