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

AI has a multiplying effect on existing technical skills

joshwcomeau.com

Post reply on HN
Print view View original

71–80 of 344 posts

Re: AI has a multiplying effect on existing technical skills

#71

Post by JumpCrisscross »

vb-8448 wrote: post #66
JumpCrisscross wrote: post #37

Earlier quoted context omitted.

> you put them in a ralph loop they can go far, far away The point is they mostly wind up somewhere stupid, and it takes expertise to spot and correct that. (Maybe that changes with further development.)

With enough time (and tokens), they'll eventually recover. It's essentially a "brute force" approach, but in most cases, they only need to succeed once.

> With enough time (and tokens), they'll eventually recover

The article’s point is this is not true. They wind up in bullshit attractors where they hit a wall and then get lost within their muddled context window.

> they only need to succeed once

Yet they don’t. Not on their own. Like, you haven’t had an LLM get stuck in a stupid loop where you point out the flaw and then it gets unstuck?

Re: AI has a multiplying effect on existing technical skills

#72

Post by kenjackson »

giancarlostoro wrote: post #53
akersten wrote: post #23

Earlier quoted context omitted.

> The code it generated was awful. The kind of garbage that people who don’t know any better would ship: it looked right and it worked. But it was instantly a maintenance dead end. In the Tailwind thread the other day I was explicitly told that the intended experience of many frameworks is "write-only code" so maybe this is just the way of the future that we have to learn to embrace. Don't worry how it's all hooked u…

Easy, have Claude review the code, tell it to be critical and that it needs to be easier to understand, follow Clean Code, SOLID principles and best practices. Lie to it, say you got this from a Junior developer, or "review it as if you were a Staff Level Engineer reviewing Junior code" the models can write better code, just nobody tells them to.

This is it. I've had a similar experience in just playing around I asked it to clean up some code it wrote to increase maintainability and readability by humans. After a few iterations it had generated quite solid code. It also broke the code a couple of times along the way. But it does get me thinking that these pipelines with agents doing specific tasks makes a lot of sense. One to design and architect, one to implement, one to clean, one to review, one to test (actually there's probably a bunch of different agents for testing -- testing perf/power, that it matches the requirements/spec, matches the design, is readable/maintainable, etc...).

Re: AI has a multiplying effect on existing technical skills

#73

Post by rob74 »

I agree with more or less everything in the article. "Agentic coding" is great, but you still need to have a good grasp of the overall architecture of your application, and actually check what the agent does, to get the best results.

The problem is just that the question is not whether "human developers will be necessary in the near future", it's "how many human developers will be necessary in the near future" - managers wanting to exploit the efficiency gains by deciding that fewer developers can now do more work "thanks" to AI.

Re: AI has a multiplying effect on existing technical skills

#74

Post by Waterluvian »

jvanderbot wrote: post #48
Waterluvian wrote: post #6

I had an Iron Man moment last week where I was “vibe coding” a UI design with component tests live on the other screen. Iterating by asking it to move things, reduce emphasis of an element, exploring layout options, etc. The loop was near realtime and felt amazing. The code it generated was awful. The kind of garbage that people who don’t know any better would ship: it looked right and it worked. But it was instantly…

I wonder how much of this is momentum. At the moment, we understand the basic tech, could reasonably DIY, but choose not to knowing full well there's a mess of understandable code somewhere we could go clean up but dont want to. We accept fast iterations because we know roughly the shape of how it "should be" and can guide an automated framework towards that. This is especially true on our own projects or something w…

Yeah that’s my main concern. It feels so so easy to be lazy and do a bad job now. And then my skills weaken and what makes me valuable fades.

I love the Iron lung reference. Perfect.

Re: AI has a multiplying effect on existing technical skills

#75

Post by furyofantares »

> So, on the one hand, I’m seeing the most talented developers I know amplify what they can do with AI, and on the other, I’m seeing people with less domain knowledge struggle to get past the “MVP” stage.

Those are people who weren't making it to the MVP stage before LLMs.

There is no doubt that highly technical people are getting A LOT more out of LLMs than people without dev experience, in an absolute sense. I think it's less clear in a relative sense.

A question I also ask myself a lot: What are the skills I'm leveraging, exactly, as a highly experienced developer that's now doing a lot of vibe coding?

1) I'm choosing good technology for the task, and thinking about what LLM-agents are good at and choosing technology that they can work well with.

2) I'm choosing good workflows for the LLM-agent, starting a new context at the right time, having it test things, making sure it has logging that it can inspect, making sure it can operate the application in a way that it can debug and inspect it.

3) I'm thinking about the code even though I'm not looking at it, I'm telling it how I want things implemented, I'm telling it how to debug things.

I think these are all hard things for non-developers to do, but I also think non-developers will be able to replicate a large chunk of #1 and #2 relatively quickly. I only have to figure out that it's valuable to tell the LLM-agent to use playwright when working on web page visuals once, and then I can tell you to do that too. Or the coding agents will come with that knowledge built-in (to the model or as a builtin skill or whatever). Knowledge around this will accumulate and become easier for non-developers to access, and in many cases be builtin to the models or harnesses.

Re: AI has a multiplying effect on existing technical skills

#76

Post by mohsen1 »

muldvarp wrote: post #28

The fact that AI currently requires some human supervision to produce valuable results is not a good predictor that it will stay this way sadly. LLMs were basically unable to reason two years ago. They are now better at many reasoning tasks than most people. If there is even a remote chance that LLMs will make your job obsolete I would pivot as fast as I could. This includes first and foremost software engineering.

I agree with you. A lot of "AI code is not clean" is hopeful thinking. In two years it might be able to design and architect better than most humans too.

Re: AI has a multiplying effect on existing technical skills

#77

Post by muldvarp »

geraneum wrote: post #70
muldvarp wrote: post #41

Earlier quoted context omitted.

I don't think it matters if the reasoning is philosophically "real" if it can solve real problems.

If you read my analogy in the context of the article, it should be clearer what I meant.

I think it would be even more clear if you just write what you mean.

Re: AI has a multiplying effect on existing technical skills

#78

Post by chrisweekly »

reconnecting wrote: post #36
pelasaco wrote: post #29

Earlier quoted context omitted.

the whole thing is creepy. The ruvnet, has multiple projects.. its just AI. A lot of AI. It floods GH infra.. Kind of easy to understand why GH struggles.

On the other hand, there are 8,400 forks, and it looks very real, so developers seem to have confidence in it.

The forks are as meaningful as the stars.

Re: AI has a multiplying effect on existing technical skills

#79

Post by giancarlostoro »

kenjackson wrote: post #72
giancarlostoro wrote: post #53

Earlier quoted context omitted.

Easy, have Claude review the code, tell it to be critical and that it needs to be easier to understand, follow Clean Code, SOLID principles and best practices. Lie to it, say you got this from a Junior developer, or "review it as if you were a Staff Level Engineer reviewing Junior code" the models can write better code, just nobody tells them to.

This is it. I've had a similar experience in just playing around I asked it to clean up some code it wrote to increase maintainability and readability by humans. After a few iterations it had generated quite solid code. It also broke the code a couple of times along the way. But it does get me thinking that these pipelines with agents doing specific tasks makes a lot of sense. One to design and architect, one to impl…

I built GuardRails after some frustrations with Beads which I love, and this whole exchange made me realize, because I have "gates" after tasks, I could add a "Review the code" type of gate, and probably get insanely better output, I already get reasonably good output because I spec out the requirements beforehand, that's the other thing, if you can tell the LLM HOW to build before it does, you will have better output.

Re: AI has a multiplying effect on existing technical skills

#80

Post by macintux »

user34283 wrote: post #45
Waterluvian wrote: post #25

Earlier quoted context omitted.

At that point the code becomes a compile target, and then you need a new source of truth. Which I think is perfectly worthy of exploration. Some people want to check in the prompts. Or even better, check in a plan.md or evenest betterest: some set of very well-defined specifications. I'm not sure what the answer will be. Probably some mix of things. But today it is absolutely imperative that the code I write for the…

I don't see the benefit of checking in either prompts or specs. I never tried spec driven development for myself, but if I review other's MRs I am typically exhausted after the first 10 lines. And there are hundreds of lines, nearly always with major inaccuracies. For myself I always found the plan mode to work well. Once the implementation is done, the code is the source of truth. If it works, it works. When I want…

I value traceability, and I value understanding the "why" of the code. For me, the prompts are useful for both.
Post reply on HN