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

221–230 of 382 posts

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

#221

Post by nly »

0xbadcafebee wrote: post #190
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…

Five hours ago I was reviewing some failed tests in a PR. The affected code was probably 300 lines, total source for the project ~1200 lines. Reading the code, I couldn't figure out what the hell was going on... and I wrote all the code. Why would that be failing? This all looks totally fine. There that should fix it! Fuck. When you write code, your brain follows a logical series of steps to produce the code, based o…

Sounds like you were just reviewing bad code.

The author should have provided context via comments and structured the code in a way that is easy to change and understand

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

#222

Post by sandos »

ekidd wrote: post #36
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…

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.

I have to 1000% agree with this. In a large codebase they also miss stuff. Actually, even at 10kloc the problems beging, UNLESS youre code is perfectly designed.

But which codebase is perfect, really?

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

#223

Post by cess11 »

BobbyJo wrote: post #102
Nition wrote: post #59

Earlier quoted context omitted.

In a way it shows how poorly we have done over the years in general as programmers in making solved problems easily accessible instead of constantly reinventing the wheel. I don't know if AI is coming up with anything really novel (yet) but it's certainly a nice database of solved problems. I just hope we don't all start relying on current[1] AI so much that we lose the ability to solve novel problems ourselves. [1]…

> In a way it shows how poorly we have done over the years in general as programmers in making solved problems easily accessible instead of constantly reinventing the wheel. I just don't think there was a great way to make solved problems accessible before LLMs. I mean, these things were on github already, and still got reimplemented over and over again. Even high traffic libraries that solve some super common proble…

"I mean, these things were on github already, and still got reimplemented over and over again."

And now people seem to automate reimplementations by paying some corporation for shoving previous reimplementations into a weird database.

As both a professional and hobbyist I've taken a lot from public git repos. If there are no relevant examples in the project I'm in I'll sniff out some public ones and crib what I need from those, usually not by copying but rather 'transpiling' because it is likely I'll be looking at Python or Golang or whatever and that's not what I've been payed to use. Typically there are also adaptations to the current environment that are needed, like particular patterns in naming, use of local libraries or modules and so on.

I don't really feel that it has made it hard for me to do because I've used a variety of tools to achieve it rather than some SaaS chat shell automation.

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

#224

Post by neoden »

Coding with AI assistants is just a completely different skill that one should not measure from the perspective of comparing it to the way human programmers write code. Mostly everything that we have: programming languages, frameworks, principles of software development in teams, agile/clean code/TDD/DRY and other debatable or well accepted practices — all this exists to overcome limitations of human mind. AI does not have them and have others.

What I found to be useful for complex tasks is to use it as a tool to explore that highly-dimensional space that lies behind the task being solved. It rarely can be described as giving a prompt and coming back for a result. For me it's usually about having winding conversations, writing lists of invariants and partial designs and feeding them back in a loop. Hallucinations and mistakes become a signal that shows whether my understanding of the problem does or does not fit.

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

#225

Post by bonesss »

raw_anon_1111 wrote: post #139
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…

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 extent lie about whether it was consulted (and then to some extent lie more about if it was then followed)? Hard yes.

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.

Lots of places have comparable design foundations as mandatory, and in some well-worn government IT processes I’m aware of the point being described is a couple man-months or man-years of actual specification away from initial approval for development.

Anyone using issue tracking will have better, searchable, tracking of “why”, and plenty of orgs mandate that from day 1. Those orgs likely are tracking contracts separately too — that kind of information is a bit special to have in a git repo that may have a long exciting life of sharing.

Subversion, JIRA, and basic CRM setups all predate GPTs public launch.

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

#226

Post by cess11 »

albert_e wrote: post #160
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.

I tried writing a plain text wordle loop as a python exercise in loops and lists along with my kid. I saved the blank file as wordle.py to start the coding while explaining ideas. That was enough context for github copilot to suggest the entire `for` loop body after I just typed "for" Not much learning by doing happened in that instance. Before this `for` loop there were just two lines of code hardcoding some words .…

This makes it really hard for juniors to learn, in my experience. When I pair with them I have them turn off that functionality so that we are forced to figure out the problems on our own and get to step through a few solutions that are gradually refined into something palatable.

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

#227

Post by thedevilslawyer »

sdf2erf wrote: post #128
SoftTalker wrote: post #107

Earlier quoted context omitted.

Filtering for people willing to jump through unreasonable hoops.

Yeah this basically. They are trying to find a particular kind of person. The people who are truly exceptional at what they do wouldnt waste their time on leetcode crap. Theyd find/create a much better alternative opportunity to allocate their precious resources toward.

they're under 1 in 1000, so the rest are that "kind" of person.

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

#228

Post by thedevilslawyer »

bayindirh wrote: post #217
thedevilslawyer wrote: post #210

Earlier quoted context omitted.

This is oft-repeated but never backed up by evidence. Can you share the snippet that was plagiarized?

While this is from 2022, here you go: https://x.com/docsparse/status/1581461734665367554 I'm sure if someone prompts correctly, they can do the same thing today. LLMs can't generate something they don't know.

That you had to look and find this from 2022 proves my point..

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

#229

Post by thedevilslawyer »

vohk wrote: post #216
thedevilslawyer wrote: post #210

Earlier quoted context omitted.

This is oft-repeated but never backed up by evidence. Can you share the snippet that was plagiarized?

I can't offer an example of code, but considering researchers were able to cause models to reproduce literary works verbatim, it seems unlikely that a git repository would be materially different. https://www.theatlantic.com/technology/2026/01/ai-memorizati...

Assuming that even works from a researcher's perspective, it's working back from a specific goal. There's 0 actual instances (and I've been looking) where verbatim code has been spat out.

It's a convenient criticism of LLMs, but a wrong one. We need to do better.

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

#230

Post by nirui »

I'm feeling people are using AI in the wrong way.

Current LLM is best used to generate a string of text that's most statically likely to form a sentence together, so from user's perspective, it's most useful as an alternative to manual search engine to allow user to find quick answers to a simple question, such as "how much soda is needed for baking X unit of Y bread", or "how to print 'Hello World' in a 10 times in a loop in X programming language". Beyond this use case, the result can be unreliable, and this is something to be expected.

Sure, it can also generate long code and even an entire fine-looking project, but it generates it by following a statistical template, that's it.

That's why "the easy part" is easy because the easy problem you try to solve is likely already been solved by someone else on GitHub, so the template is already there. But the hard, domain-specific problem, is less likely to have a publicly-available solution.

Post reply on HN