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

351–360 of 382 posts

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

#351

Post by h4kunamata »

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…

>It's obviously easier to verify something is correct than come up with the correct thing in the first place.

You are missing the biggest root cause of the problem you describe: People write code differently!

There are "cough" developers whose code is copy/paste from all over the internet. I am not even getting into the AI folks going full copy/paste mode.

When investigating said code, you will be like why this code in here?? You call tell when a python script contains different logic for example. Sure, 50 lines will be easy to ready, expand that to 100 lines and you be left on life support.

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

#352

Post by AuthAuth »

ThunderSizzle wrote: post #116
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.

I've seen many discussions stating patent hoarding has gone too far, and also that copyright for companies have gone way too far (even so much that Amazon can remove items from your purchase library if they lose their license to it). Then AI begins to offer a method around this over litigious system, and this becomes a core anti-AI argument. I do think it's silly to think public code (as in, code published to the pub…

I'm not using this as an anti AI argument. I'm saying if they arent going to respect IP law then no one should and I dont want to hear them moan or go after anyone stealing their IP.

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

#353

Post by peteforde »

lanstin wrote: post #345
peteforde wrote: post #19

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 a…

Things that claude code/vibe coding is great at: 1. Allowing non-developers to provide very detailed specs for the tools they want or experiences they are imagining 2. Allowing developers to write code using frameworks/languages they only know a bit of and don't like; e.g. I use it to write D3 visualizations or PNG extracts from datastores all the time, without having to learn PNG API or modern javascript frameworks.…

I just don't get it.

Why do all of that when you can just keep a tight hold on an agent that is operating at the speed that you can think about what you're actually doing?

Again, if you're just looking to spend a lot of money on the party trick, don't let me yuck your yum. It just seems like doing things in a way that is almost guaranteed to lead to the outcomes that people love to complain aren't very good.

As someone getting excellent results on a huge (550k LoC) codebase only because I'm directing every feature, my bottleneck is always going to be the speed at which I can coherently describe what needs to be done + a reasonable amount of review to make sure that what happened is what I was looking for. This can only work because I explicitly go through a planning cycle before handing it to the agent.

I feel like if you consider understanding what your LLM is doing for you to be unacceptably slow and burdensome, then you deserve exactly what you're going to get out of this process.

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

#354

Post by hyperadvanced »

datsci_est_2015 wrote: post #320
hyperadvanced wrote: post #78

Earlier quoted context omitted.

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.

> 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. Unit testing is my number one use case for gen AI in SWE. I just find the style / concept often slightly different than I would personally do, so I end up editing the whole thing. But, it’s great at getting me p…

Totally. I’m a huge fan of it, but it rarely “just” works and I do have to babysit it to make sure it’s actually doing something good for the world

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

#355

Post by hyperadvanced »

00deadbeef wrote: post #187
minimaxir wrote: post #96

Earlier quoted context omitted.

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.

Opus 4.5 successfully ignored the first line of my CLAUDE.md file last week

Thank god it’s not just me. It really makes me feel insane reading some of the commentary online.

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

#356

Post by sigseg1v »

qlm wrote: post #339
sigseg1v wrote: post #328

Earlier quoted context omitted.

To add on to this, I see many complaints that "[AI] produced garbage code that doesn't solve the problem" yet I have never seen someone say "I set up a verification system where code that passes the tests and criteria and code that does not is identified as follows" and then say the same thing after. To me it reads like saying "I typed pseudocode into a JS file and it didn't compile , JS is junk". If people learn to…

At that point why not just have an actual deterministic transpiler?

I feel that the devil is in the edge cases and this allows you to have the freedom to say "ok I want to try for 1.0 match between everything, I can accept 0.98 match, and files which have less of a match it can detail notes for and I can manually approve them". So for things where the languages differ too much for specific patterns such as maybe an event handing module, you can allow more leniency and tell it to use the target languages patterns more easily, without having to be so precise as to define every single transformation as you would with a transpiler.

In short: because it's faster and more flexible.

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

#357

Post by blirio »

The article describes the problems of using a AI chat app without setting up context, skills, MCP, etc

Like yea the AI won’t know what you discussed in last weeks meeting by default. But if you do auto transcribe to your meetings (even in person just open zoom on one persons laptop), save them to a shared place and have everyone make this accessible in their LLM’s context then it will know.

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

#358

Post by wredcoll »

crazygringo wrote: post #154
layer8 wrote: post #147

Earlier quoted context omitted.

> But in order to write the code, you might have to try 4 different top-level approaches until you figure out the one that works , try integrating with a function from 3 different packages until you find the one that works properly If you haven’t spent the time to try the different approaches yourself, tried the different packages etc., you can’t really judge if the code you’re reading is really the appropriate thing…

The goal isn't usually to determine whether the function is the perfect optimal version of the function that could ever exist, if the package it integrates with the the best possible package out of the 4 mainstream options, or to become totally and intimately familiar with them to ensure it's as idiomatic as possible or whatever. You're just making sure it works correctly and that you understand how. Not superficiall…

I can read a line of code and tell you that it's storing a pointer in this array cell and removing this other pointer and incrementing this integer by 6 and so on. None of that tells me if that is the correct thing to be doing.

Detecting obvious programming errors like forgetting to check for an error case or freeing a variable or using an array where a set should be is, usually, obvious, and frequently machine can and will point it out.

Knowing that when you add a transaction to this account you always need to add an inverse transaction to a different account to keep them in sync is unlikely to be obvious from the code. Or that you can't schedule an appointment on may 25th because it's memorial day. Or whatever other sorts of actually major bugs tend to cause real business problems.

I mean, sure, if someone documented those requirements clearly and concisely and they were easy to find from the section of code you were reviewing such that you knew you needed to read them first, then yes, it becomes a lot easier. My experience as a professional programmer is this happens approximately never, but I suppose I could be an outlier.

And yes if you want to be extremely literal, some code is easier to read than write. But no one cares about that type of code.

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

#359

Post by wredcoll »

jama211 wrote: post #333
layer8 wrote: post #147

Earlier quoted context omitted.

> But in order to write the code, you might have to try 4 different top-level approaches until you figure out the one that works , try integrating with a function from 3 different packages until you find the one that works properly If you haven’t spent the time to try the different approaches yourself, tried the different packages etc., you can’t really judge if the code you’re reading is really the appropriate thing…

Outside of life saving critical software or military spec software, no one needs to review so hard they understand it to the level you’re describing, and they do not. There is a mathematical principle that verification of a proof is easier than any proof. The same is true in code.

I mean, it's even easier to just not read the code in the first place, I'm not sure what that proves, other than perhaps an implicit collorary to the original quote "reading code is quite hard (so people rarely bother)"

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

#360

Post by wredcoll »

jama211 wrote: post #334
crazygringo wrote: post #145

Earlier quoted context omitted.

That doesn't make any sense to me. When the code is written, it's all laid out nicely for the reader to understand quickly and verify. Everything is pre-organized, just for you the reader. But in order to write the code, you might have to try 4 different top-level approaches until you figure out the one that works, try integrating with a function from 3 different packages until you find the one that works properly, h…

Well said, you’re absolutely right. In practice code review is orders of magnitude faster than code creation and it always has been, baffling anyone is arguing otherwise. Perhaps they’ve never worked in a real organisation, or they’ve only worked on safety critical code,m or something?

Sometimes code review is so fast it's literally instant (because people aren't actually reading the code).

I think it's one of those sort of, dunno, wink wink situations where we all know that doing real in depth code reviews would take way more time than the managers will give (and generally isn't worth it anyways) so we just scan for obvious things and whatever happens to interact with our particular speciality in the code base.

Post reply on HN