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

251–260 of 382 posts

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

#251

Post by laserlight »

swordsith wrote: post #71
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.

Once, I told a friend that it was stupid that Claude Code didn't have native IDE integration. His answer: “You don't need an IDE with Claude Code.”

I've begun to suspect response that this technology triggers a kind of religion in some people. The technology is obviously perfect, so that any problems you might have are because of you.

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

#252

Post by xigoi »

Dylan16807 wrote: post #188
ibeckermayer wrote: post #152

Earlier quoted context omitted.

1. Equality under the law is important in its own right. Even if a law is wrong, it isn’t right to allow particular corporations to flaunt it in a way that individuals would go to prison for. 2. GPL does not allow you to take the code, compress it in your latent space, and then sell that to consumers without open sourcing your code.

> 1. Equality under the law is important in its own right. Even if a law is wrong, it isn’t right to allow particular corporations to flaunt it in a way that individuals would go to prison for. We're talking about the users getting copyright-laundered code here. That's a pretty equal playing field. It's about the output of the AI, not the AI itself, and there are many models to choose from.

> there are many models to choose from.

There don’t seem to be any usable open-source models.

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

#253

Post by r-w »

fsmv wrote: post #172
phpnode wrote: post #133

Earlier quoted context omitted.

The other day I had an agent write a parser for a niche query language which I will not name. There are a few open source implementations of this language on github, but none of them are in my target language and none of them are PEGs. The agent wrote a near perfect implementation of this query language in a PEG. I know that it looked at the implementations that were on github, because I told it to, yet the result is…

It would be nice to give them some kind of attribution in the readme or something since you know which projects you referenced

Exactly. If you have the decency to ask, you probably have the capacity to be courteous beyond the minimum required by law.

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

#254

Post by xigoi »

anoncow wrote: post #31
le-mark wrote: post #9

I vibe coded a retro emulator and assembler with tests. Prompts were minimal and I got really great results (Gemini 3). I tried vibe coding the tricky proprietary part of an app I worked on a few years ago; highly technical domain (yes vague don’t care to dox myself). Lots of prompting and didn’t get close. There are literally thousands of retro emulators on github. What I was trying to do had zero examples on GitHub…

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…

Breaking down a problem in simpler terms that a computer can understand is called coding. I don’t need a layer of unpredictability in between.

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

#255

Post by xigoi »

EnPissant wrote: post #194
mattgreenrocks wrote: post #108

Earlier quoted context omitted.

Yet it still fumbles even when limiting context. Asked it to spot check a simple rate limiter I wrote in TS. Super basic algorithm: let one action through every 250ms at least, sleeping if necessary. It found bogus errors in my code 3 times because it failed to see that I was using a mutex to prevent reentrancy. This was about 12 lines of code in total. My rubber duck debugging session was insightful only because I h…

Try again with gpt-5.3-codex xhigh.

The goalposts have been moved so many times that they’re not even on the playing field.

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

#256

Post by NitpickLawyer »

bonesss wrote: post #225
raw_anon_1111 wrote: post #139

Earlier quoted context omitted.

I agree completely. I just did my first “AI native coding project”. Both because for now I haven’t run into any quotas using Codex CLI with my $20/month ChatGPT subscription and the company just gave everyone an $800/month Claude allowance. Before I even started the implementation I: 1. Put the initial sales contract with the business requirements. 2. Notes I got from talking to sales 3. The transcript of the initial…

> Can you say that about any project that was done before GenAI? … a project with a decomposition of top level tasks, minutes and meeting notes, a transcript, initial diagrams, a bunch of loose transcripts on soon to be outdated assumptions and design, and then a soon-to-be-outdated living and constantly modified AGENT file that will be to some extent added to some context and to some extent ignored and to some exten…

> soon to be outdated assumptions

Wild assumption. Having docs and code in step has never been easier.

> soon-to-be-outdated living and constantly modified AGENT file

Quite contradictory.

> I have absolutely seen far better initial project setups that are more complete, more focused, more holistically captured, and more utilitarian for the forthcoming evolution of design and system.

From a single dev, in a day's work? I call massive bs on this.

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

#257

Post by rjsw »

20k wrote: post #181
AuthAuth wrote: post #54

Earlier quoted context omitted.

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.

This is why its astonishing to me that AI has passed any legal department. I regularly see AI output large chunks of code that are 100% plagiarised from a project - its often not hard to find the original source by just looking up snippets of it. 100s of lines of code just completely stolen Ai doesn't actually wash licenses, it literally can't. Companies are just assuming they're above the law

If the LLM was trained on any GPL licenced code then there is an argument that all output is GPL too, legal departments should be worried.

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

#258

Post by housecarpenter »

crazygringo wrote: post #141

> Reading and understanding other people's code is much harder than writing code. I keep seeing this sentiment repeated in discussions around LLM coding, and I'm baffled by it. For the kind of function that takes me a morning to research and write, it takes me probably 10 or 15 minutes to read and review. It's obviously easier to verify something is correct than come up with the correct thing in the first place. And…

The reason I don't spend the majority of my time in code review is that when I'm reviewing my teammates' code I trust that the code has already been substantially verified already by that teammate in the process of writing it and testing it. Like 90% verified already. I see code review as just one small stage in the verification process, not the whole of it.

The way I approach it, it's really more about checking for failures, rather than verifying success. Like a smoke test. I scan over the code and if anything stands out to me as wrong, I point it out. I don't expect to catch everything that's wrong, and indeed I don't (as demonstrated by the fact that other members of the team will review the code and find issues I didn't notice). When the code has failed review, that means there's definitely an issue, but when the code has passed review, my confidence that there are no issues is still basically the same as it was before, only a little bit higher. Maybe I'm doing it wrong, I don't know.

If I had to fully verify that the code was correct when reviewing, applying the same level of scrutiny that I apply to my own code when I'm writing, I feel like I'd spend much longer on it---a similar time to what I'd spend writing on it.

Now with LLM coding, I guess opinions will differ as to how far one needs to fully verify LLM-generated code. If you see LLMs as stochastic parrots without any "real" intelligence, you'll probably have no trust in them and you'll see the code generated by the LLM as being 0% verified, and so as the user of the LLM you then have to do a "review" which is really going from 0% to 100%, not 90% to 100% and so is a much more challenging task. On the other hand, if you see LLMs as genuine intelligences you'd expect that LLMs are verifying the code to some extent as they write it, since after all it's pretty dumb to write a bunch of code for somebody without checking that it works. So in that case, you might see the LLM-generated code as 90% verified already, just as if it was generated by a trusted teammate, and then you can just do your normal review process.

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

#259

Post by baq »

xigoi wrote: post #254
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…

Breaking down a problem in simpler terms that a computer can understand is called coding. I don’t need a layer of unpredictability in between.

by the time you're coding your problem should be broken down to atoms; that isn't needed anymore if you break it down to pieces which LLMs can break down to atoms instead.

'need' is orthogonal.

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

#260

Post by mountainb »

satvikpendem wrote: post #185
ibeckermayer wrote: post #152

Earlier quoted context omitted.

1. Equality under the law is important in its own right. Even if a law is wrong, it isn’t right to allow particular corporations to flaunt it in a way that individuals would go to prison for. 2. GPL does not allow you to take the code, compress it in your latent space, and then sell that to consumers without open sourcing your code.

> 2. GPL does not allow you to take the code, compress it in your latent space, and then sell that to consumers without open sourcing your code. If AI training is found to be fair use, then that fact supercedes any license language.

Fair use is a case by case fact question dependent on many factors. Trial judges often get creative in how they apply these. The courts are not likely to apply a categorical approach to it like that despite what some professors have written.
Post reply on HN