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

141–150 of 204 posts

Re: The role of developer skills in agentic coding

#141

Post by tomrod »

ferguess_k wrote: post #38

I don't really like AI in IDE. I don't want them to think for me. Code completion and Intellisense is good enough. That said, I think there are 3 items that are important: - Quickly grasp a new framework or a new language. People might expect you to do so because of AI's help. 2 weeks might be the maximum, instead of the minimum. The same for juniors. - Focus on the real important things. So instead of trying to memo…

For me I have two extremes:

1. Complete Vibe coding -- greenfield and just playing or doing a small quick prototype

2. Get out of my IDE, but know my code base -- small snippets, methods, classes that add desired functionality but off to the side completely -- and don't run things in my shell that's just wrong

What I don't like it current codebases getting whacked because it decided to downgrade a dependency or lie about a function signature.

Re: The role of developer skills in agentic coding

#143

Post by tomrod »

danmur wrote: post #97
AndyNemmity wrote: post #77

Earlier quoted context omitted.

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?

Most people have a smaller context window than LLMs.

Re: The role of developer skills in agentic coding

#144

Post by nikolayasdf123 »

adamgordonbell wrote: post #31

Lack of reuse AI-generated code sometimes lacks modularity, making it difficult to apply the same approach elsewhere in the application. Example: Not realising that a UI component is already implemented elsewhere, and therefore creating duplicate code. Example: Use of inline CSS styles instead of CSS classes and variables This is the big one I hit for sure. I think it's a problem with agentic RAG, where it only knows…

yep. noticed this too. but I think this is due to short context LLMs have. now my tools, mostly browser LLMs copy-paste code, are analysing small sub-problem at time. once LLMs will see whole repository + history of that repository, likely they will write abstractions that can be reused

Re: The role of developer skills in agentic coding

#145

Post by owebmaster »

echoangle wrote: post #132
owebmaster wrote: post #126

Earlier quoted context omitted.

It is definitely not unfair. #2 is a great strategy, I'm gonna try in my agentic tool. We obviously need experts to steer the AIs in this current phase, who said we don't?

> We obviously need experts to steer the AIs in this current phase, who said we don't? I don't know if it's explicitely said but if you call it agentic, it sounds like it can do stuff independently (like an agent). If I still need to hand feed it everything, I wouldn't really call it agentic.

There are two different roles here, the dev that creates the agent and the user that uses the agent. The user should not need to adapt/edit prompts but the dev definitely should for it to evolve. Agents aren't AGI, after all.

Re: The role of developer skills in agentic coding

#146

Post by nikolayasdf123 »

DeathArrow wrote: post #94

Imo, AI implements something useful 20% of the time while breaking existing code 80% of the time.

which AIs are you using? do you edit what they suggest yourself or just blindly copy-paste and hit run? do you ask them to write unit-tests + self-fix for what they written?

Re: The role of developer skills in agentic coding

#147

Post by nikolayasdf123 »

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?

LLMs writing Go is so hot right now

Re: The role of developer skills in agentic coding

#148

Post by nikolayasdf123 »

jillesvangurp wrote: post #32

I use LLMs for various purposes in day to day development. I don't use any of the tools mentioned in the article because I'm using intellij and don't want to replace a tool that has lots of stuff that I use all the time. But aside from that, it's good advice and matches my experience. I've dabbled with plugins for intellij but wasn't really happy with those. But ever since chat gpt for desktop started interfacing dir…

this. very similar experience. but toolset is rather different.

Re: The role of developer skills in agentic coding

#149

Post by nikolayasdf123 »

jstanley wrote: post #8
mjr00 wrote: post #6

> 15k LOC codebase I wish articles about AI assistance would caveat this at the start. 15k LOC is a weekend hackathon project, which is all well and good, but not reflective of the work that 99% of developers are doing in their day jobs.

I, too, habitually write 7500 lines of code per day.

what are you guys writing? is this like unit tests/generated files or something? or some non-reusable constant definitions(CSS/JSON/YAML)?

Re: The role of developer skills in agentic coding

#150

Post by BigParm »

dingnuts wrote: post #127
ikerino wrote: post #104

Earlier quoted context omitted.

> Is that really hype? I'm thinking back to various promises self-driving would be widespread by 2016. These set a certain expectation for how our roads would look that I don't think has been realized a decade later (even as I've ridden in Waymos/FSD Teslas.)

if Elon Musk hadn't convinced the world in 2015 that self driving cars were right around the corner, that could work with just a few sensors and machine learning, maybe we'd have smart highways now. Slightly less fancy technology communicating hazards and such to cars from sensors on the road. But no, we have Waymo, I guess, so that means Musk was right?

The best choice is to do it right the first time, instead of spending billions in infrastructure which soon becomes obsolete.
Post reply on HN