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

11–20 of 382 posts

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

#11

Post by airstrike »

Forgeties79 wrote: post #8
Trufa wrote: post #5

[flagged]

> It's so intriguing, I wonder if the people who are against it haven't even used it properly. I feel like this is a common refrain that sets an impossible bar for detractors to clear. You can simply hand wave away any critique with “you’re just not using it right.” If countless people are “using it wrong” then maybe there’s something wrong with the tool.

Illogical.

I had Claude read a 2k LOC module on my codebase for a bug that was annoying me for a while. It found it in seconds, a one line fix. I had forgotten to account for translation in one single line.

That's objectively valuable. People who argue it has no value or that it only helps normies who can't code or that sooner or later it will backfire are burying their heads in the sand.

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

#12

Post by zythyx »

Trufa wrote: post #5

[flagged]

> I wonder if the people who are against it haven't even used it properly.

I swear this is the reason people are against AI output (there are genuine reasons to be against AI without using it: environmental impact, hardware prices, social/copyright issues, CSAM (like X/Grok))

It feels like a lot of people hear the negatives, and try it and are cynical of the result. Things like 2 r's in Strawberry and the 6-10 fingers on one hand led to multiple misinterpretations of the actual AI benefit: "Oh, if AI can't even count the number of letters in a word, then all its answers are incorrect" is simply not true.

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

#13

Post by Zigurd »

It's pretty difficult to say what it's going to be three months from now. A few months ago Gemini 2.x in IDEA and related IDEs had to be dragged through coding tasks and would create dumb build time errors on its way to making buggy code.

Gemini in Antigravity today is pretty interesting, to the point where it's worth experimenting with vague prompts just to see what it comes up with.

Coding agents are not going to just change coding. They make a lot of detailed product management work obsolete and smaller team sizes will make it imperative to reread the agile manifesto and and discard scrum dogma.

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

#14

Post by seanmcdirmid »

Trufa wrote: post #5

[flagged]

HN has a huge anti AI crowd that is just as vocal and active as its pro AI crowd. My guess that this is true of the industry today and won’t be true of the industry 5 years from now: one of the crowds will have won the argument and the other will be out of the tech industry.

Vibe coding and slop strawmen are still strawmen. The quality of the debate is obviously a problem

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

#15

Post by fHr »

as usual the last 20% need 80% and the other 80% need 20% but my god did Ai make my bs corpo easy repeatable shit work like skimming docs writing summaries, skimming jira confluence and so on actually easier and for 90% of bs crud app changes the first draft is also already pretty good tbh I don't write hard/difficult code more then once a week/month.

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

#16

Post by seanmcdirmid »

Forgeties79 wrote: post #8
Trufa wrote: post #5

[flagged]

> It's so intriguing, I wonder if the people who are against it haven't even used it properly. I feel like this is a common refrain that sets an impossible bar for detractors to clear. You can simply hand wave away any critique with “you’re just not using it right.” If countless people are “using it wrong” then maybe there’s something wrong with the tool.

There are people who know how to code and people who don’t. AI is the same way, it isn’t a mystery.

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

#17

Post by hippo22 »

Forgeties79 wrote: post #8
Trufa wrote: post #5

[flagged]

> It's so intriguing, I wonder if the people who are against it haven't even used it properly. I feel like this is a common refrain that sets an impossible bar for detractors to clear. You can simply hand wave away any critique with “you’re just not using it right.” If countless people are “using it wrong” then maybe there’s something wrong with the tool.

> If countless people are “using it wrong” then maybe there’s something wrong with the tool.

Not really. Every tool in existence has people that use it incorrectly. The fact that countless people find value in the tool means it probably is valuable.

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

#18

Post by kfarr »

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 don't think AI is a panacea, it's just knowing when it's the right tool for the job and when it isn't.

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

#19

Post by peteforde »

Daily agentic user here, and to me the problem here is the very notion of "vibe coding". If you're even thinking in those terms - this idea that never looking at the code has become a goal unto itself - then IMO you're doing LLM-assisted development wrong.

This is very much a hot take, but I believe that Claude Code and its yolo peers are an expensive party trick that gives people who aren't deep into this stuff an artificially negative impression of tools that can absolutely be used in a responsible, hugely productive way.

Seriously, every time I hear anecdotes about CC doing the sorts of things the author describes, I wonder why the hell anyone is expecting more than quick prototypes from an LLM running in a loop with no intervention from an experienced human developer.

Vibe coding is riding your bike really fast with your hands off the handles. It's sort of fun and feels a bit rebellious. But nobody who is really good at cycling is talking about how they've fully transitioned to riding without touching the handles, because that would be completely stupid.

We should feel the same way about vibe coding.

Meanwhile, if you load up Cursor and break your application development into bite sized chunks, and then work through those chunks in a sane order using as many Plan -> Agent -> Debug conversations with Opus 4.5 (Thinking) as needed, you too will obtain the mythical productivity multipliers you keep accusing us of hallucinating.

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

#20

Post by arnonejoe »

Totally agree on ai assisted coding resulting in randomly changed code. Sometimes it’s subtle and other times entire methods are removed. I have moved back to just using a JetBrains IDE and coping files in to Gemini so that I can limit context. Then I use the IDE to inspect changes in a git diff, regression test everything, and after all that, commit.
Post reply on HN