LLMs reward expertise • Hacker News Board

Re: LLMs reward expertise

#481

Post by godwinson__4-8 » Tue, Aug 04, 2026, 12:59 PM UTC

friendzis wrote: post #470

bartread wrote: post #429

Earlier quoted context omitted.

Interesting, but... wrong tool, wrong job. And by tool, I mean web based chat interface, not LLMs in general. (Maybe wrong delivery mechanism, if you like.) Your friend needed an agent, not a chatbot. I use Claude within VS Code (as per many others) but I certainly wouldn't recommend that for a beginner. They needed a tool that's specifically aimed at people who want to build software but don't know the first thing a…

What makes this anecdote hard to believe is that seemingly two things happened simultaneously: 1. The layperson was able to to steer the session(-s) into full PM/PO mode ideating, refining and explaining features and ideas. 2. The user was the sycophant in this relationship, never steering the session(-s) into producing something tangible. The premise supposes that somehow the session(-s) never even tangentially touc…

Indeed. It reads like software engineer employment cope by appealing to the lowest common denominator possible. As if solutions for that type of end user weren't already solved for over a decade ago, most of which now have agents built in.

It just is not believable or interesting. Even if it did happen, the reality is it just doesn't matter.

Re: LLMs reward expertise

#482

Post by perrygeo » Tue, Aug 04, 2026, 1:04 PM UTC

LLMs are language models. So much of this can be reduced to a simple heuristic: If you can't think clearly, LLMs will not help you. If you don't know what you're asking for or how to express it precisely, it really should not be a surprise that the output is garbage. Failures of LLMs are more often failures of our own brain to consider the problem clearly. That's harder to admit than just blaming the AI.

It's important to note though, from the perspective of the LLM's objective function, that this is not a failure at all! LLMs are designed to match patterns. You give a jumbled mess of incoherent ideas, it will faithfully reproduce a token stream of incoherent ideas. It's only when the model output is subjected to the real world that it fails.

Re: LLMs reward expertise

#483

Post by econ » Tue, Aug 04, 2026, 1:08 PM UTC

Im beginning to think buzzword bingo is a viable job interview method.

If you use the b words the LLM would be somewhat constrained to content that has them. If you don't use them it will use content that doesn't have them.

The company website (subject) will never become a static html document. If you request exactly what static html does it should probably point you to a wysiwyg website builder.

Re: LLMs reward expertise

#484

Post by andrew_lettuce » Tue, Aug 04, 2026, 1:11 PM UTC

_joel wrote: post #464

bartread wrote: post #459

Earlier quoted context omitted.

No, not really. My HR friend went out and found Lovable on her own. You're acting like people can't Google, or even ask an LLM via a Chatbot interface for recommendations for tools that would help them build an application as an absolute beginner. They can and do. People have agency, which is exactly why this person's friend asked them for help.

They were literally in front of an LLM. Did they ask for tools? edit: Lovable is a web app too, not an agent.

This comment - and many others - misses the OP's original point: what are tools? Do you mean my laptop, and a pen and paper? What's an agent? I.D.E.? none of this is part of the vocabulary or context of someone who has never built things with a computer, let alone AI. Years ago I had a neighbor who was trying to learn how to use their computer; they complained that the book they were using was only telling them all the DOS and none of the DON'TS. This is were most people start.

Re: LLMs reward expertise

#485

Post by balderdash » Tue, Aug 04, 2026, 1:12 PM UTC

I haven’t experienced this - or maybe the training data for aviation is limited. But ask a an llm for aircraft performance / flight planning data and it’s scary how bad the advice /feed back is.

Re: LLMs reward expertise

#486

Post by defgeneric » Tue, Aug 04, 2026, 1:14 PM UTC

znnajdla wrote: post #294

defgeneric wrote: post #250

Earlier quoted context omitted.

Exactly. The post read to me as another variation of the denial that people with expertise are reaching for right now. My sense is that we as programmers went through it over a year ago already (perhaps not all of us, but at least anyone paying attention), and so it's easy to overlook that it's still new to people who do other forms of "knowledge work," i.e. people whose identity is bound up with their expertise. My…

What sort of denial are you reading into the author's post? I don't read it as denial. He is fully acknowledging the usefulness of AI.

He's saying: "Expertise improves AI-assisted work, experts can steer better and get more out of models."

The obvious conclusion for anyone is "therefore experts will remain the indispensable and specially rewarded center of the production process."

That this is appearing exactly now, and in this form, strikes me as extremely suspicious. I don't doubt the author's sincerity on the surface. What I suspect is that anxiety over the possibility that the (unstated) conclusion might be false (!) motivates the argument in the first place.

I'm asking the question, "Why is this argument appearing now?" At least one reason seems to me to be, "because we're afraid of what the world could look like if it's not true."

Re: LLMs reward expertise

#487

Post by andrew_lettuce » Tue, Aug 04, 2026, 1:18 PM UTC

friendzis wrote: post #299

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…

> They didn’t even get to that point. Because my friend didn’t have the vocabulary to ask the AI to write code. What harness did you use? In e.g. claude, there are two modes: 1. Spit out code 2. Draft a plan, ask questions, GOTO 1 You literally have to go out of your way to get it NOT to write code. I keep mine on a tight-ish leash because it modify code way too happily even when there's no intention or instruction t…

How would an absolute newbie know what a harness is? What an IDE is? That code is represented in a set of files? That some of those files are actually metadata? What metadata is? What GOTO means? That you're suggesting a modified SDLC?

None of this is related to intelligence, desire or potential. It's about context and experience. The vast majority of people use their computers as consumption devices, like a TV. If I asked you to "make a movie" where would you start?

Re: LLMs reward expertise

#488

Post by giancarlostoro » Tue, Aug 04, 2026, 1:27 PM UTC

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…

Every now and then I'll write a single prompt to Claude to see how much of a web app I can build in one shot. I usually pick Django (though I assume any other web framework could suffice) because of the battery included nature, I still sometimes describe that I want users to login / register, have access to x, y, z

I also noticed a friend of mine had way more success by having Claude write code by doing TDD and giving Claude scenarios for things the code should be able to handle, if you do this correctly, and cover edge cases, Claude will work with these in mind.

Re: LLMs reward expertise

#489

Post by throwatdem12311 » Tue, Aug 04, 2026, 1:29 PM UTC

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…

Weird because I had a friend that wanted a web app, also no experience, and he just told Claude (on the iOS app) to make it for him and Claude just made an artifact and put everything there.

Buddy sent me a share link and he was just like “dude this is crazy I just told it what I wanted and it just spit it out in a few minutes”. No “experiment” needed he just did it because he knew Claude could do it and it worked exactly like you’d expect. Hell, he did it on the Free tier.

Re: LLMs reward expertise

#490

Post by yashpatelcode » Tue, Aug 04, 2026, 1:32 PM UTC

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've seen the same thing happen to my brother when he tried making an app with zero experience. Only difference was that he got a front end that didn't work.