Live data from Hacker News

AI has a multiplying effect on existing technical skills

joshwcomeau.com

281–290 of 344 posts

Re: AI has a multiplying effect on existing technical skills

#281
> Without guidance, LLMs tend to paint themselves into a corner, because they’re generating code to solve individual prompts, not thinking holistically about an application’s architecture.

Yes this is what I have been experiencing as well. I kind of live in a bubble around my own technical expertise, but it seemed only natural that you would have to guide the model. I'm new to AI as of February. Someone suggested I use it to upgrade my Hugo site and that was all I needed. No I am converting a CRM to obsidian and Rewriting some Obsidian plug-ins to do what I want them to do.

For example, I am using an Obsidian plug-in to do presentations from my markdown files "Advanced Obsidian Slides" but it styles the slides using absolute styling. Every time I tried to the prompt model to improve display elements in that styling I spent a lot of time asking it to go back and try something else to get the results I wanted.

Finally I decided to rewrite the plugin with a fluid design with in the fixed boundary of the slides. Instead of using floats I switched to Flexboxes and all my problems were solved in one-shot situations.

The moral of the story is don't expect the model to do what you want it to do without the proper framework. And research correct terms, you will save yourself a lot of time prompting/writing instruction docs that the LLM will end up implementing.

Re: AI has a multiplying effect on existing technical skills

#282

Earlier quoted context omitted.

I'm pretty you wouldn't want the same for code that runs healthcare, banks or transport. Only useless shitty web projects could embrace what's you're saying. And no there's no "Claude review the code and improve it" magical formula

I work in the health software space and there are tons of internal tools which aren't production code that can benefit massively from throwaway "write-only code". Putting a web UI on top of a management CLI tool so support ops can run things without needing an oncall engineer can be a huge win. I recently built a testing UI that doubles a demo-scenario-setup tool. Is it well-engineered? Who cares - it pokes the right…

> internal tools which aren't production code that can benefit massively from throwaway "write-only code".

First of all internal tools just prove my point. Second can't wait to hear a story of a health care production database blown away because someone was playing with generated tools that "pokes the right things".

We NEED end user experiences that don't suck, and don't keep getting shittier like now, not being able to use a cli for internal tools, it's a skill issue, not everythint needs a shitty ui that taps into an os system calls and blows away as soon as the cli responds with something unexpected

Re: AI has a multiplying effect on existing technical skills

#283
post #121

The more time I spend accelerating my work with AI tools the more I realize how incredibly hard the craft of shipping useful software actually is. Sure, Claude Code and Codex can write (most of) the code for me - but the amount of technical knowledge I need to decide what and how to build remains enormous. As an example: I'm working on a system right now that works like Claude Artifacts, allowing custom HTML+JS apps…

> It really saddens me to see some developers talk about literally quitting their careers over AI, right when the benefits of existing deep technical experience have never been more valuable.

But that's not what senior executives think. That's all that matters. If they think that AI can replace engineers, so let it be. I mean, since when senior executives know shit about what quality means? They only care about revenue and profit. So yeah, you're right, but that's not gonna happen (sadly)

Re: AI has a multiplying effect on existing technical skills

#284

Earlier quoted context omitted.

I work in the health software space and there are tons of internal tools which aren't production code that can benefit massively from throwaway "write-only code". Putting a web UI on top of a management CLI tool so support ops can run things without needing an oncall engineer can be a huge win. I recently built a testing UI that doubles a demo-scenario-setup tool. Is it well-engineered? Who cares - it pokes the right…

> internal tools which aren't production code that can benefit massively from throwaway "write-only code". First of all internal tools just prove my point. Second can't wait to hear a story of a health care production database blown away because someone was playing with generated tools that "pokes the right things". We NEED end user experiences that don't suck, and don't keep getting shittier like now, not being able…

You still have to do the engineering parts of software engineering, you can't just turn off your brain and vibe. Just like you can't with hand-written code. I've seen what an intern with access to prod DB can do.

For example, the testing tool I built explicitly doesn't work in production environment. That was part of my design spec and I manually verified the code and behavior.

Re: AI has a multiplying effect on existing technical skills

#285
post #121

The more time I spend accelerating my work with AI tools the more I realize how incredibly hard the craft of shipping useful software actually is. Sure, Claude Code and Codex can write (most of) the code for me - but the amount of technical knowledge I need to decide what and how to build remains enormous. As an example: I'm working on a system right now that works like Claude Artifacts, allowing custom HTML+JS apps…

“ the more I realize how incredibly hard the craft of shipping useful software actually”.

I posted something here not long ago re. There is a huge amount of craftsmanship in between a great idea and great product. And it received a lot of downvotes.

LLM’s don’t change this in reality. That’s why we haven’t seen an explosion of high value products. Creating a product in the first place that create value is VERY, VERY HARD! The arrogance of people to dismiss it because of the existence llm’s is hilarious.

Re: AI has a multiplying effect on existing technical skills

#286

I also "had an Iron Man moment last week" as a mathematician. I've been doing joint math research with two friends (professors) on a project for several years. Last week, I decided to explore part of our research using chat GPT. 1) I would have a thought. 2) Present it to GPT. 3) Ask GPT to write theorems that were easy to prove and put those proofs into LaTeX. (I always have to check the proofs carefully.) 4) Then I…

So why are you using ChatGPT?

Re: AI has a multiplying effect on existing technical skills

#287
post #229

Earlier quoted context omitted.

I think the key word is ability , and I fully agree with that. Using GenAI as a teaching aid can supercharge learning, especially as it makes it very easy to learn by doing. The problem is that people use GenAI to do and hence don't learn. (The preliminary research so far supports this: using AI to do the hard assignments produces poor learning outcomes, but using AI as a tutor, or even just for help with the hard as…

> using AI as a tutor, or even just for help with the hard assignments, produces slightly better learning outcomes Source? The few people I’ve seen try to do this wind up with a terrible understanding of the material, with large knowledge gaps and one or two fundamental fuckups. In every case, an introductory textbook would have been better. (It would also have been harder.)

I think many on here are legit delusional and often talk about subjects with a lot of confidence when they clearly have a lot of mangled/broken knowledge - e.g. finance.

Re: AI has a multiplying effect on existing technical skills

#288

I think that it's not a multiplier on skills. It's a reducer of time . For less experienced developers, it's an immediately reduction at the start of a project. But then they will almost certainly have problems later when their initial decisions come back to haunt them. For senior devs, it's like having a junior or mid-level dev that will instantly do things within their capability, so long as it's explained to them…

> I think that it's not a multiplier on skills.

I'm not sure. It's a reducer on time to refine and adopt skills, if you're interested. I know that's somewhat pedantic, but there really is a skill multiplier if that's what you want out of it.

I'm far, far better at using AWS than I was after years of using it (for better or worse). I use the command line more effectively than ever. These are real skills that have come to me as a result of that reduction of time to get the answers I wanted. This applies to all kinds of things in my work, and it's been quite liberating to have this incredible tightening of temporal scales in order to get where I'd like to be, resulting in actual differences in my own outputs and capabilities.

Still, I agree that time really is a key facet. I could have found this information before, too. It just took so long to do it.

Re: AI has a multiplying effect on existing technical skills

#289

I think that it's not a multiplier on skills. It's a reducer of time . For less experienced developers, it's an immediately reduction at the start of a project. But then they will almost certainly have problems later when their initial decisions come back to haunt them. For senior devs, it's like having a junior or mid-level dev that will instantly do things within their capability, so long as it's explained to them…

It can spit out a utility bash or python script lightning fast, which is a real game changer.

I wanted to run a stupid little webserver on one of my raspis, so I just asked Gemini to write my the code, along with a bash script to set up the proper configs to run as a systemd service. Nothing I couldn't basically do in my sleep, but it takes some amount of time and focus to do.

In the time it took me to write this comment, it wrote exactly what I needed. Not that impressive in isolation, but now I've been doing all the little home automation things I never had the energy for with other responsibilities.

Re: AI has a multiplying effect on existing technical skills

#290
post #278

Earlier quoted context omitted.

using AI to write your own personal software whose quality is only concerned by you, the user. If it works for you, it works for you. This will be the norm in the future. SaaS and platforms and the old way of writing software will die when writing software becomes something one does while asleep.

Ah I see. Funny enough I consider myself more of a dinosaur or originalist- the PC was idealized as a device for individuals to write their own programs for their personal use. The issue before is that coding is not only difficult and time-consuming to learn, but also that I think it requires a particular type of person to fully grasp this new, non-human language. I see these SOTA LLMs as akin to the digital camera r…

Yup, same lens, different revolution. The issue now is it's not just photography that's more accessible. It's all creative endeavours. Writing (including software) included.
Post reply on HN