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

LLMs reward expertise

seangoedecke.com

Post reply on HN
Print view View original

381–390 of 605 posts

Re: LLMs reward expertise

#381

Post by RileyJames »

wongarsu wrote: post #368
roncesvalles wrote: post #276

Earlier quoted context omitted.

>We've seen plenty of examples of apps successfully vibe coded by non technical people, including apps making real revenue. Have we? Or is this just something that people say now, without citation?

Maybe people don't cite specific apps because they like their jobs, and outing apps as vibe-coded is still seen as negative I personally know of two completely vibe-coded large apps in my professional environment. One by a non-technical manager, made to solve his needs, then sold to customers. Initial development went along great, but by now velocity has greatly slowed down. Also took a lot of engineering hours (of a…

> Honestly it should have stayed as a prototype that then gets rebuilt from the ground up.

And that’s a natural process for many products. In the journey from discovery to prototype to MVP to product, it should be rebuilt multiple times.

Particularly with LLM’s to assist, the process of rebuilding from a new context and understanding of the desired goal requires even less effort.

The hardest part is managing any real users, their expectations, and any data / workflows they’ve come to require from what came before.

Re: LLMs reward expertise

#382

Post by walthamstow »

Maxion wrote: post #360
vector_spaces wrote: post #330

Earlier quoted context omitted.

I'm genuinely a bit floored reading the comments here, but I guess my idea of the average HN commenter's ability to talk to non-technical folks about technical topics is biased because I work and socialize with lots of people who don't have technical expertise (thankfully along with other technical folks who also have lots of experience talking to the former group). Many of them don't even know what Claude is, let al…

The average person does not even know what ChatGPT is and has not interacted with an LLM ever.

I don't think this is true. Certainly not in Britain.

I went to 3 weddings last summer and each one had a joke in a speech about using ChatGPT to write it and everyone laughed. 68yo father of the bride is a retired plumber and even he's cracking jokes about AI.

Re: LLMs reward expertise

#383

Post by josephg »

RileyJames wrote: post #374
imhoguy wrote: post #328

Earlier quoted context omitted.

As decades-exp SWE I love using Claude Design for any kind of app and web development, because it gives much faster visual feedback loop than changing views within deep framework stack. It much easier to "tell" coding agent what I need instead of writing wall of prose to define visual stuff. I reminds me old WYSIWYG and unlike Figma it has full HTML/CSS capabilities available. How I work with it: - I ask agent to ext…

I’ve been curious on how to close this loop between engineering and design/product. We don’t use react, which Claude design seems to trend towards. We use Phoenix / liveview. We have a shared design system, which keeps the visual elements in line. And then just prototype on design, collab, discuss and arrive at what we want to ship. And then engineering take over and rebuild via hand / claude code. But the tools aren…

I think the way humans divide up design and programming are broadly correct. Working that way with LLMs seems to work well.

I vibe coded an iOS conference schedule app recently, built on top of my own rust UI framework. I started with claude design. I gave it the requirements, and showed it screenshots of other conference schedule apps I like which have features I want to use. I also gave it some visual references for how I want the app styled. It came up with some workable designs. They were a bit 'webby'. But, fine. The high level breakdown of UI screens and navigation between them was excellent.

Then I gave all the HTML files it produced to claude code, along with the documentation for my UI framework and told it to port the code to my UI framework. The first working version was rough. It copied a lot of the unintentional webby look and feel. It worked around missing features in my UI framework by rolling its own janky reimplementations of platform features. For example, instead of using UINavigationController, it rolled its own. It made its own (kinda bad) tab based navigation bar. The app didn't work properly in dark mode, because it was hard-coding a lot of colours. It took a bit of back and forth to fix all of this stuff. But I'm really happy with it now. It looks and feels great.

It's just a pity I couldn't share the app at the conference. Apple took a few days to approve the app in Testflight, and by the time they approved it, the conference was over.

I assume everyone else is playing with the same AI tools that I am, and getting similar results. But a lot of people I talk to seem to have no idea that this is possible right now. They're amazed when I show them my schedule app.

Re: LLMs reward expertise

#384

Post by sensanaty »

vector_spaces wrote: post #330
harvey9 wrote: post #323

Earlier quoted context omitted.

Knowing what Claude Code is and why you might want it actually is domain knowledge which the op's friend does not have. Your idea of the average person might be biased if you work and socialise with people who have this kind of expertise.

I'm genuinely a bit floored reading the comments here, but I guess my idea of the average HN commenter's ability to talk to non-technical folks about technical topics is biased because I work and socialize with lots of people who don't have technical expertise (thankfully along with other technical folks who also have lots of experience talking to the former group). Many of them don't even know what Claude is, let al…

Yeah it's a true HN bubble moment. I've got non-technical people in my company (a tech company, where the majority of the employees are engineers) who have absolutely no idea what any of the agentic coding nonsense is, their only exposure to this stuff is Gemini in Google's office apps.

To them this is all just "AI" whether it comes from OpenAI, Anthropic or Google - hell they probably don't even know what an LLM is in the first place, yet alone which company provides what tooling. And these are people whose day-to-day involves talking to at least 1 dev a day, so you would imagine some of the knowledge would materialize via osmosis at the very least.

Re: LLMs reward expertise

#385

Post by bjackman »

> The model outputs are much more concise than when I try and talk to GPT-5.6 Sol about mathematics. By signalling expertise, Tao shunts the model into “talking-to-mathematicians”

Maybe, but FWIW my first thought when I skimmed Tao's session was that he probably has a personal system prompt requesting this style.

E.g. even if you get it into "talking to an expert" mode I've found AI waffling through filler like "given your background in Linux kernel engineering, I'll skip the surface level and go straight to the technical meat". You do have to explicitly tell them if you don't want this.

Re: LLMs reward expertise

#386

Post by ben_w »

ElectricalUnion wrote: post #218
davely wrote: post #201

Earlier quoted context omitted.

Perhaps! But I do think the vocabulary issue is real and I think LLMs are still sycophantic enough that they won’t really challenge someone or offer alternative ideas on how to implement something unless they explicitly ask. Interestingly at my work, Claude Code was available before Claude Desktop, so a number of non-technical PMs tried to use it in order to build… anything, with very mixed success. The “hey guys, ch…

> the terminal is a scary place Isn't the the powerful, unlimited, unopinionated blank LLM text input waiting for your instructions eerily similar to a scary terminal? WIMP and GUI paradigms are the exact the opposite: intentional dis-empowering, by design restrictions, enumeration of your few possible options. Those feel more constrained therefore safer.

> Isn't the the powerful, unlimited, unopinionated blank LLM text input waiting for your instructions eerily similar to a scary terminal?

This is why it has the title (for me currently reading "What can I help with?" but this varies a lot) and the text box itself has the placeholder text "Ask anything". Sometimes I get big friendly suggestions about what to ask it, placed on screen near that text box.

> WIMP and GUI paradigms are the exact the opposite: intentional dis-empowering, by design restrictions, enumeration of your few possible options. Those feel more constrained therefore safer.

I don't think it's constraints, per se: almost nobody looks at the font list and goes "oh no, too many options!"

Rather, GUIs are there to organise your options visually, group them in ways easy to intuitively get. There's a bit of fashion-induced rot here, e.g. I'm old enough to remember when it was always unambiguous when you were looking at a checkbox vs. a radio button, and now there's a blurry middle ground of collections of boxes with ticks in them that act mutually exclusive, but the point of a GUI from a UX POV is not the same as how software in general drifted as it got both more users and more developers and more opinionated managers and middle managers and designers who only cared about shiny rather than usability.

Re: LLMs reward expertise

#387

Post by bjackman »

krisoft wrote: post #191

I did a test a few months ago. A friend of mine wanted to develop what i understood to be a simple single page web app. But since she didn’t have any software engineering experience she asked me to help. Around that time everyone was talking about how literally anyone can develop software with LLMs i asked her if she could give it a try first, and if I could watch the attempt. I was fully expecting that writing the c…

I have been pondering this and I think it's likely a gap that will get filled sooner or later.

Right now there's just so much value in building LLM tools for experts that everyone is focusing on that. But surely at some point we'll have bespoke harnesses that exist exactly to solve this kind of thing.

I think this can start with constrained problem spaces like "you are a WordPress developer, you solve problems for people with enough expertise to know they are looking for a WordPress developer" and incrementally expand from there. Maybe I'm naive but I think you can probably get pretty far with this today just by writing loads of skills and picking the right technical preferences to encode in them.

Re: LLMs reward expertise

#389

Post by Cthulhu_ »

bjackman wrote: post #387
krisoft wrote: post #191

I did a test a few months ago. A friend of mine wanted to develop what i understood to be a simple single page web app. But since she didn’t have any software engineering experience she asked me to help. Around that time everyone was talking about how literally anyone can develop software with LLMs i asked her if she could give it a try first, and if I could watch the attempt. I was fully expecting that writing the c…

I have been pondering this and I think it's likely a gap that will get filled sooner or later. Right now there's just so much value in building LLM tools for experts that everyone is focusing on that. But surely at some point we'll have bespoke harnesses that exist exactly to solve this kind of thing. I think this can start with constrained problem spaces like "you are a WordPress developer, you solve problems for pe…

Yeah there's lots of companies out there that promise that people can build a website quickly, often using WYSIWYG / drag / drop interfaces, I bet they already have AI integration to speed things up. ("I bet" because I don't actually use those services.)

I think people are better helped by using those services than going a level lower and using LLMs directly.

Re: LLMs reward expertise

#390

Post by lionkor »

petcat wrote: post #80
lionkor wrote: post #70

Earlier quoted context omitted.

This "instant" loop is so fast because it doesn't involve the part where you learn

You seem to be hung up on the part about "learning". Do you know how x86 registers work? Or atomic instructions available on ARM, SPARC, or POWER architectures? No, of course not. Because all of that got abstracted to higher-level instructions decades ago.

> Do you know how x86 registers work? Or atomic instructions available on ARM, SPARC, or POWER architectures?

Yeah, I have a pretty good idea of how we go from code -> IR registers -> x86 registers and how the underlying hardware has more registers than that, etc.

As for SPARC and POWER, I have not yet gotten my hands on one! But as someone who writes compilers for fun I did learn about most of that, yes.

I write C# in my dayjob, and having written high-ish performance C++ and Rust for a couple years before that, and because of all the curiosity-driven projects I've done (like writing useless compilers), I did learn a lot.

This has helped me massively in my job, especially when optimizing our C# sensor data ingestion backend to process hundreds of thousands of measurements per seconds with explicit backpressure etc. it was great fun because I know what I'm doing.

I'm not trying to "uhm actually" you, but when you call yourself a software engineer, I do expect that you know some of these things after some years in the industry. The only way you wouldn't is a lack of curiosity, or because you genuinely had no idea that you CAN learn these things.

Post reply on HN