FR version is available. Content is displayed in original English for accuracy.
Advertisement
Advertisement
⚡ Community Insights
Discussion Sentiment
53% Positive
Analyzed from 2341 words in the discussion.
Trending Topics
#code#don#llm#llms#write#better#apps#where#human#why
Discussion (87 Comments)Read Original on HackerNews
At the same time, I think we're far too far down the systems path now. We've hit a point where interviewing has become purely systems design "because the AI writes the code".
Not that I'm ever asked, but I inherently believe the act of critical thinking, communication, and expression are the key skills for those who already have the appropriate coding/engineering/cs/etc background. I now only interview for those skills - but through the lens of impossible to solve systems design conversations as opposed to problems. It tells me a lot about how people think.
But you effectively lose the human review component.
I mean, I'm proud of my low-level skills too but this is some Fabrice Bellard level sorcery. Very, very few humans are able to do this without AI tools.
- is it understandable
- is it maintainable
- how much work is adding new features
- is it written in a way that adding new features means rewriting a lot of it
- is it written in a consistent style
- and lots of other things
I use AI to write a lot of my code, but the only time it's clearly "better" than a competent human is for one-off things.
That being said - AI + human is, without any doubt in my mind, better than either one alone.
Agentic engineering faces all kinds of new problems that couldn’t exist before, and need experienced engineers to solve them.
Just because you don’t seem to be interested in the answer - then don’t read it? - doesn’t make the question wrong.
GPT 5.6 sol and Astra can now one shot incredible stuff.
LLM is incredibly valuable for debugging complex problems, codebase exploration, and planning large changes. But the writing code part itself, I find, LLMs are just not very good at it yet.
Yubico Authenticator https://github.com/Yubico/yubioath-flutter
I actually don't see any significant signs of AI use. There's Copilot listed in the contributor list, but I'm not seeing commits listed under it. Did they wipe it off Github?
Some seem to stamp Mostly AI based on weaker circumstantial like large init commits. Maybe it's just an artifact of human sloppiness.
Or maybe it was just the artifact of choosing these by last update, since vibe-coded apps genuinely do have an abnormal number of releases, and thus would be much more likely to show up.
I use the contributor graph to find where the AI made the commits [1] and then I search using the date [2], I found 3 commits relative to a11y stuff.
[1] https://github.com/Yubico/yubioath-flutter/graphs/contributo...
[2] https://github.com/Yubico/yubioath-flutter/commits/main/?sin...
It would be too annoying for a human to ever write code to standards this high, and would have taken me months to write by hand, but with the help of AI I was able to get it done and built in a way I can easily review and reason about.
I have a memory safe baremetal tiny linux init now built to my exact requirements.
AI can help experienced engineers write better code in less time.
If you're as productive as an engineer in 2016, you're not at the level that's expected. A 7 day workflow back then should take you maybe a day or less to work on today.
What are the AI smells there?
It would be nice to expand a bit on the reasoning behind the verdicts.
I will be curious to see how I feel about AdventOfCode this year...
Because then why do you ride a vehicle when you could walk?
Why do you use fire when a well-positioned mirror with sun could do?
Why a piezo ignition or lighter when a stick and lots of friction would do as well?
””” F-Droid is not hosted in just any data center where commodity hardware is managed by some unknown staff. We worked out a special arrangement so that this server is physically held by a long time contributor with a proven track record of securely hosting services. We can control it remotely, we know exactly where it is, and we know who has access. ”””
I find it strange how little people seem to care these days and just widely share their users and company data across clouds. Plenty of supply chain attacks to learn from.
Separate from building your own code, ,of course you may have your own standards to apply.
But for apps, well, I never had a chance to see how good or bad the code was before AI was about, so why should I care now, so long as what I paid for does what it says it does (and nothing nefarious..)
The blog post provides something akin to answer to this question:
You see, the main allure of LLMs is that they allow the developer to be more lazy. That’s kind of the whole point! You just prompt, sit back and relax. So it should not surprise you to hear that this attitude is then reflected in everything the vibe-coder touches
As I understand it, one of concerns is that with the lowered barriers there comes a flood of low quality software, vibe coded by very lazy and not very talented people.
This might be actually more of a human problem, but it's a problem nevertheless.
I fail to see why worrying about AI code quality is any different to worrying about developer code quality when it comes to pre packaged apps.
With code I am writing, some AI generated, my work load has not really decreased, nor have I gotten lazy. My work has changed to a degree, and now involves reviewing and guiding and double checking AI code where I did not have to before, but I am certainly still working just as hard, and accomplishing more with AI's help in spite of the change in workload it brings.
delivering bad AI code because you got lazy is not the AI fault, it's the developers fault.
I haven't done that at all.
> Make no mistakes
Don't forget the copium!