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

The role of developer skills in agentic coding

martinfowler.com

Post reply on HN
Print view View original

91–100 of 204 posts

Re: The role of developer skills in agentic coding

#91

Post by chrisco255 »

ikerino wrote: post #12

I use Cursor for most of my development these days. This article aligns pretty closely with my experiences. A few additional observations: 1. Anecdotally, AI agents feel stuck somewhere circa ~2021. If I install newer packages, Claude will revert to outdated packages/implementations that were popular four years ago. This is incredibly frustrating to watch and correct for. Providing explicit instructions for which pac…

I don't see the 2021 problem as much with Grok, but it is wired up to X for realtime learning, it can also fetch and crawl pages. Occasionally I'll use dev branch of some codebase, like Zig, and I just have to let it know the version I'm on and remind it to use the dev version. Occasionally I'll have to paste in the new API and then it works out what the answer should be.

A lot of the other problems mentioned still hold though.

Re: The role of developer skills in agentic coding

#92

Post by nukem222 »

ikerino wrote: post #12

I use Cursor for most of my development these days. This article aligns pretty closely with my experiences. A few additional observations: 1. Anecdotally, AI agents feel stuck somewhere circa ~2021. If I install newer packages, Claude will revert to outdated packages/implementations that were popular four years ago. This is incredibly frustrating to watch and correct for. Providing explicit instructions for which pac…

I agree with all of this. I want to offer a tiny bit more hope, though:

> There have been a lot of bold promises (and genuine advances), but I don't see a world in the next 5 years where AI writes useful software by itself.

I actually think the opposite: that within five years, we will be seeing AI one-shot software, not because LLMs will experience some kind of revolution in auditing output, but because we will move the goalposts to ensure the rough spots of AI are massaged out. Is this cheating? Kind of, but any effort to do this will also ease humans accomplishing the same thing.

It's entirely possible, in other words, that LLMs will force engineers to be honest about the ease of tasks they ask developers to tackle, resulting in more easily composable software stacks.

I also believe that use of LLMs will force better naming of things. Much of the difficulty of complex projects comes from simply tracking the existence and status of all the moving parts and the wires that connect them. It wouldn't surprise me at all if LLMs struggle to manage without a clear shared ontology (that we naturally create and internalize ourselves).

Re: The role of developer skills in agentic coding

#95

Post by petesergeant »

ikerino wrote: post #12

I use Cursor for most of my development these days. This article aligns pretty closely with my experiences. A few additional observations: 1. Anecdotally, AI agents feel stuck somewhere circa ~2021. If I install newer packages, Claude will revert to outdated packages/implementations that were popular four years ago. This is incredibly frustrating to watch and correct for. Providing explicit instructions for which pac…

> Spot on. Current environment feels like the self-driving car hype cycle. There have been a lot of bold promises (and genuine advances), but I don't see a world in the next 5 years where AI writes useful software by itself.

My worry is that we get an overnight sea-change like 4o image generation. The current tools aren't good enough for anything other than one-shotting, and then suddenly overnight, they're good enough to put a lot of people out of work.

Re: The role of developer skills in agentic coding

#96

Post by re-thc »

ikerino wrote: post #12

I use Cursor for most of my development these days. This article aligns pretty closely with my experiences. A few additional observations: 1. Anecdotally, AI agents feel stuck somewhere circa ~2021. If I install newer packages, Claude will revert to outdated packages/implementations that were popular four years ago. This is incredibly frustrating to watch and correct for. Providing explicit instructions for which pac…

> Current environment feels like the self-driving car hype cycle.

Is that really hype? I mean there companies or person(s) hyping it up, but there is also Waymo and Pingshan (Baidu) for example actually rolling it out. It's a lot less hype than AI coding.

> Anecdotally, AI agents feel stuck somewhere circa ~2021.

That's only part of the problem. It's also stuck or dead set on certain frameworks / libraries where it has training data.

> I keep thinking about The Tortoise and The Hare.

This implies that AI is currently "smart". The hare is "smarter" and just takes breaks i.e. it can actually get the job done. With the current "AI" there are still quirks where it can get stuck.

Re: The role of developer skills in agentic coding

#97

Post by danmur »

AndyNemmity wrote: post #77
aschearer wrote: post #40

I've been using Claude to help write a complex prototype for game dev. Overall it's been a big productivity boost. However as the project has grown Claude has gotten much worse. I'm nearing 15k lines and it's borderline more trouble than it's worth. Even when it was helpful, it needed a _lot_ of guidance from me. Almost more helpful as a "rubber ducky" and for the fact that it kept me from deadlocking on analysis. Th…

Why not just split the tasks, and have different projects only house a portion of the code?

Why dumb down your work worse because the machine can't understand it?

Re: The role of developer skills in agentic coding

#98

Post by danmur »

cheevly wrote: post #81
svilen_dobrev wrote: post #44

i have mentored a few people to become Programmers. Some for months, some for years. It's like teaching someone to ride a bycicle. Hand-holding first, then hand-guiding, then short flights, then longer... Different people pick stuff at different pace and shape.. but they do learn.. if they want to. What i completely miss in these LLM parrots-agents-generators, is the learning. You can't teach them anything. They woul…

Literally all of this is easy to solve if you actually tried. Developers are literally too lazy to write their own AI tooling, it’s bizarre to me.

The goal isn't to use AI, though, it's to be productive. Maybe for you AI + writing support tools to improve your workflow makes you more productive and that's great! For me, for the kind of work I'm currently doing, I'm more productive in other ways.

Re: The role of developer skills in agentic coding

#100

Post by Derbasti »

nottorp wrote: post #86

Does anyone post articles about using these LLMs on non web dev? The internet is full of javascript/html/css info. Some wrong some obsolete some right and current, but there is data. How about the more peasant languages?

Anecdotally, it does somewhat fine with C++ and OpenCV. Python is great, though PySide much less so. QML is almost useless. GLSL is OK, but not great. It generally can't reason well across language barriers, although it's great at converting between languages.

The deeper into a nerdy domain I go, the less likely it is to understand what's going on. And more broadly, it seems that usefulness steeply declines for larger files and projects. It just can't fit enough context into its window to make sense of complicated things.

As an extreme example, I told it to average two angles, and it just took the mean of them. Even after prompting, it thought nothing wrong of that. (The average of 1° and 359° is 0°, not 180°.) So it goes for many domains outside of webdev, UI, data science, scripting.

Post reply on HN