Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Senior Developer Skills in the AI Age

manuel.kiessling.net

Post reply on HN
Print view View original

141–150 of 323 posts

Re: Senior Developer Skills in the AI Age

#141

Post by thesnide »

lolinder wrote: post #81
Aurornis wrote: post #36

Earlier quoted context omitted.

> I feel like one could delete almost all comments from that project without losing any information I far from a heavy LLM coder but I’ve noticed a massive excess of unnecessary comments in most output. I’m always deleting the obvious ones. But then I started noticing that the comments seem to help the LLM navigate additional code changes. It’s like a big trail of breadcrumbs for the LLM to parse. I wouldn’t be surpr…

It doesn't hurt that the model vendors get paid by the token, so there's zero incentive to correct this pattern at the model layer.

or the model get trained from teaching code which naturally contains lots of comments.

the dev is just lazy to not include them anymore, wheres the model doesn't really need to be lazy, as paid by the token

Re: Senior Developer Skills in the AI Age

#142

Post by achierius »

bongodongobob wrote: post #48
imiric wrote: post #18

Earlier quoted context omitted.

> They’re very good at honing bad code into good code with good feedback. And they're very bad at keeping other code good across iterations. So you might find that while they might've fixed the specific thing you asked for—in the best case scenario, assuming no hallucinations and such—they inadvertently broke something else. So this quickly becomes a game of whack-a-mole, at which point it's safer, quicker, and easie…

This typically happens when you run the chat too long. When it gives you a new codebase, fire up a new chat so the old stuff doesn't poison the context window.

But it rarely gives me a totally-new codebase unless I'm working on a very small project -- so I have to choose between ditching its understanding of some parts (e.g. "don't introduce this bug here, please") and avoiding confusion with others.

Re: Senior Developer Skills in the AI Age

#143

Post by triyambakam »

mjr00 wrote: post #33
ramesh31 wrote: post #28

Earlier quoted context omitted.

>The scary thing is: I have seen professional human developers write worse code. This is kind of the rub of it all. If the code works, passes all relevant tests, is reasonably maintainable, and can be fitted into the system correctly with a well defined interface, does it really matter? I mean at that point its kind of like looking at the output of a bytecode compiler and being like "wow what a mess". And it's not li…

> If the code works, passes all relevant tests, is reasonably maintainable, and can be fitted into the system correctly with a well defined interface, does it really matter? You're not wrong here, but there's a big difference in programming one-off tooling or prototype MVPs and programming things that need to be maintained for years and years. We did this song and dance pretty recently with dynamic typing. Developers…

The ML world being nearly entirely in Python, much of it untyped (and that the Python type system is pretty weak) is really scary.

Re: Senior Developer Skills in the AI Age

#144

Post by barrell »

rybosome wrote: post #11
necovek wrote: post #9

The premise might possibly be true, but as an actually seasoned Python developer, I've taken a look at one file: https://github.com/dx-tooling/platform-problem-monitoring-co... All of it smells of a (lousy) junior software engineer: from configuring root logger at the top, module level (which relies on module import caching not to be reapplied), over not using a stdlib config file parser and building one themselves,…

Ok - not wrong at all. Now take that feedback and put it in a prompt back to the LLM. They’re very good at honing bad code into good code with good feedback. And when you can describe good code faster than you can write it - for instance it uses a library you’re not intimately familiar with - this kind of coding can be enormously productive.

I would not say it is “very good” at that. Maybe it’s “capable,” but my (ample) experience has been the opposite. I have found the more exact I describe a solution, the less likely it is to succeed. And the more of a solution it has come up with, the less likely it is to change its mind about things.

Every since ~4o models, there seems to be a pretty decent chance that you ask it to change something specific and it says it will and it spits out line for line identical code to what you just asked it to change.

I have had some really cool success with AI finding optimizations in my code, but only when specifically asked, and even then I just read the response as theory and go write it myself, often in 1-15% the LoC as the LLM

Re: Senior Developer Skills in the AI Age

#145

Post by ManuelKiessling »

thisdougb wrote: post #2

This is interesting, thanks for posting. I've been searching for some sort of 'real' usage of AI-coding. I'm a skeptic of the current state of things, so it's useful to see real code. I know Python, but have been coding in Go for the last few years. So I'm thinking how I'd implement this in Go. There's a lot of code there. Do you think it's a lot, or it doesn't matter? It seems reasonably clear though, easy to unders…

With this project, I was really only interested in the resulting application, and intentionally not in the resulting code.

I really wanted to see how far I can get with that approach.

I will ask it to clean up the code and its comments and report back.

Re: Senior Developer Skills in the AI Age

#146

Post by ManuelKiessling »

noodletheworld wrote: post #45

> Once again, the AI agent implemented this entire feature without requiring me to write any code manually. > For controllers, I might include a small amount of essential details like the route name: [code] Commit history: https://github.com/dx-tooling/platform-problem-monitoring-co... Look, I honestly think this is a fair article and some good examples, but what is with this inane “I didn’t write any of it myself” c…

True, this needs to be fixed.

What I wanted to express was that I didn’t do any of the implementation, that is, any logic.

I need to phrase this better.

Re: Senior Developer Skills in the AI Age

#147

Post by ManuelKiessling »

williamdclt wrote: post #31
ramesh31 wrote: post #22

This maps pretty well to my experience. Other devs will say things like "AI is just a stupid glorified autocomplete, it will never be able to handle my Very Special Unique Codebase. I even spent 20 minutes one time trying out Cursor, and it just failed" Nope, you're just not that good obviously. I am literally 10x more productive at this point. Sprint goals have become single afternoons. If you are not tuned in to wh…

Giving your anecdotal experience is only useful if you include anecdotal context: seniority, years of experience, technology, project size, sprint goal complexity…

You are not wrong! I will add those infos.

Re: Senior Developer Skills in the AI Age

#148

Post by ramesh31 »

triyambakam wrote: post #143
mjr00 wrote: post #33

Earlier quoted context omitted.

> If the code works, passes all relevant tests, is reasonably maintainable, and can be fitted into the system correctly with a well defined interface, does it really matter? You're not wrong here, but there's a big difference in programming one-off tooling or prototype MVPs and programming things that need to be maintained for years and years. We did this song and dance pretty recently with dynamic typing. Developers…

The ML world being nearly entirely in Python, much of it untyped (and that the Python type system is pretty weak) is really scary.

>The ML world being nearly entirely in Python, much of it untyped (and that the Python type system is pretty weak) is really scary

I think this has a ton to do with the mixed results from "vibe coding" we've seen as the codebase grows in scope and complexity. Agents seem to break down without a good type system. Same goes for JS.

I've just recently started on an Objective-C project using Cline, and it's like nirvana. I can code out an entire interface and have it implemented for me as I'm going. I see no reason it couldn't scale infinitely to massive LOC with good coding practices. The real killer feature is header files. Being able to have your entire projects headers in context at all time, along with a proper compiler for debugging, changes the game for how agents can reason on the whole codebase.

Re: Senior Developer Skills in the AI Age

#149

Post by carpo »

crm9125 wrote: post #119
carpo wrote: post #63

Earlier quoted context omitted.

I'm the complete opposite. After being burnt out and feeling an almost physical repulsion to starting anything new, using AI has renewed my passion. I've almost finished a side project I started 4 weeks ago and it's been awesome. Used AI from the beginning for a Desktop app with a framework I'd never heard of before and the learning curve is almost non-existent. To be able to get the boring things done in minutes is…

Similar sentiment here. I taught myself python a decade ago after college, and used it in side projects, during my masters degree, in a few work projects. So it's been handy, but also required quite a bit of time and effort to learn. But I've been using Claude to help with all kinds of side projects. One recently was to help create and refine some python code to take the latest Wikipedia zipped XML file and transform…

That's awesome! That's a lot of data and a great speed increase. I think that as long as you test and don't just accept exactly what it outputs without a little thought, it can be really useful.

I take it as an opportunity to learn too. I'm working on a video library app that runs locally and wanted to extract images when the scene changed enough. I had no idea how to do this, and previously would have searched StackOverflow to find a way and then struggled for hours or days to implement it. This time I just asked Aider right in the IDE terminal what options I had, and it came back with 7 different methods. I researched those a little and then asked it to implement 3 of them. It created an interface, 3 implementations and a factory to easily get the different analyzers. I could then play around with each one and see what worked the best. It took like an hour. I wrote a test script to loop over multiple videos and run each analyzer on them. I then visually checked the results to see which worked the best. I ended up jumping into the code it had written to understand what was going on, and after a few tweaks the results are pretty good. This was all done in one afternoon - and a good chunk of that time was just me comparing images visually to see what worked best and tweaking thresholds and re-running to get it just right.

Re: Senior Developer Skills in the AI Age

#150

Post by lloeki »

Henchman21 wrote: post #96
gerdesj wrote: post #71

Earlier quoted context omitted.

My current favourite LLM wankery example is this beauty: https://blog.fahadusman.com/proxmox-replacing-failed-drive-i... Note how it has invented the faster parameter for the zpool command. It is possible that the blog writer hallucinated a faster parameter themselves without needing a LLM - who knows. I think all developers should add a faster parameter to all commands to make them run faster. Perhaps a LLM could cr…

What makes you think this was created by an LLM? I suspect they might actually have a pool named faster -- I know I've named pools similarly in the past. This is why I now name my pools after characters from the Matrix, as is tradition.

The pool is named backups according to zpool status and the paragraph right after.

But then again the old id doesn't match between the two commands.

Post reply on HN