Live data from Hacker News

LLMs reward expertise

seangoedecke.com

291–300 of 606 posts

Re: LLMs reward expertise

#291

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?

.

That was kinda harnessed and prompted by a team of security experts, so there's that.

Re: LLMs reward expertise

#292

Earlier quoted context omitted.

LLMs skew toward over-focusing on things that you mention. The reason "the agent suddenly started suggesting all kinds of things to make its code more robust" is because you said you "want to build reliable software". It's not a signal of good judgment or understanding. It's just how LLM attention works.

I thought exactly the same at first. But then i wondered if that still holds true with today's advanced thinking, RLHF involved, frontier models. I guess to a certain extend it did indeed behave better, as a reaction to his self description into account. EDIT: I mean, those systems accumulated so much complexity around the attention based next token predictor.

Yeah, in my experience, there's nothing about:

1. LLM thinking 2. RLHF 3. The latest frontier models

that does anything to change this fundamental "suggestibility" of LLMs.

But who knows, maybe I'm wrong.

Re: LLMs reward expertise

#293
post #275

Earlier quoted context omitted.

It uses javascript. Still a static file. Lets you play chess

Don’t you update the DOM to render the pieces as they’re moved?

A static website is one that doesn’t have an associated backend API server, just serves as one or more self contained file assets.

The files you serve to the browser are static, not the contents of the page itself

Updating the dom can happen with only individual assets, so it’s a static site

Re: LLMs reward expertise

#294

Not sure I agree with this. The math guy at anthropic's prompts are essentially: "suppose you’ve gotta resolve the $CONJECTURE, like absolutely have to, everything depends on it. think really hard, and try to come up with a bunch of ideas to try. but remember to trust yourself and not necessarily in conventional wisdom!!" https://claude.ai/share/25740bd5-aa97-4bd7-bf58-c4df3793fda7 https://xcancel.com/__alpoge__/stat…

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.

Re: LLMs reward expertise

#295

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?

Plinq. Plinq was made on Lovable, https://www.aieatingtheworld.com/articles/non-technical-foun... Couple more on https://buildthedamnthing.com/resources/articles/case-studie...

Wow, I am not sure that I want my safety app to be videcoded by someone without experience

Re: LLMs reward expertise

#296
Of course they do. They have such a huge parameter maps. You need to be able to guide it through the map, so it starts making the right connections. Even in the Sonnet 3.7 days, it became clear to me, that if I have want efficient code out of it, I need to really take care of the context. If I just let it research a problem, it will mess up most of the time. If I tell it to study A, B, C and then present problem D, it will solve it perfectly. And it's true even with the current top models.

Re: LLMs reward expertise

#297

Earlier quoted context omitted.

They probably mean static site, in the sense of static front end, no backend.

Yes. That's not an app.

The person you responded too didn't mention app though. They just said static. OP was talking about an app but the responded was hypothesizing about something static.

Anyway I'm not so sure "static" is a viable boundary between app and not app. A static page that does any sort of API request doesn't suddenly become an app imo.

Re: LLMs reward expertise

#298

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…

OTOH my wife's friends got drunk and made "tinder for horse purchases". They prompted to read typical horse advertisements (we're all horse people) and create an app with mock tinder like entries to swipe right and left to buy horses. A web app was produced with lots of mock "Hi i'm Dominique and i love running through fields and having a bucking good time" type entries complete with silly horse photos. A huge amount…

> The little apps i made here and there before AI are being outdone by a bunch of drunk people on a whim!

Yes, but the premise of the article is you should be able to outdo a bunch of drunk people with your 30 years experience, if you use AI too.

Re: LLMs reward expertise

#299

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 to do so

Re: LLMs reward expertise

#300

Earlier quoted context omitted.

We've seen plenty of examples of apps successfully vibe coded by non technical people, including apps making real revenue. Your friend could start with telling the LLM that they are a non technical person who wants to make an app and it will explain all the successive steps.

>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?

A friend of mine, non-technical, is not making money with his apps. But he's creating a street fighter like game. Just for fun.

So there's that.

He can't exactly release it because he uses a lot of copyrighted stuff. It's also meant only for himself. Though, I've been asking if I can play it, it looks fun.

Post reply on HN