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

461–470 of 607 posts

Re: LLMs reward expertise

#461

Post by bartread »

datenyan wrote: post #439
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…

Isn’t that kinda the point, though? If you already lack the required knowledge to ask a web-based chat UI (which, as an aside, is almost exclusively referring to ChatGPT Free for the average user) to build a HTML page, how could you possibly know to go search for Lovable, let alone figure out agents? I feel as though the gap between the theoretical power of LLMs and what the average user knows of them and their capab…

> how could you possibly know to go search for Lovable, let alone figure out agents?

Is this an actually serious question? Am I losing my mind here?

I didn't tell my HR friend about Lovable: she found it on her own. Of course someone's not going to Google for Lovable if they've never heard of it, but they might Google for "how do I build a website without knowing anything about it?", or ask ChatGPT the same question.

They're also, most likely, getting endless ads for AI services that help you build various kinds of software shoved into their faces all the time - these ads may not couch the value ad in exactly these terms, but that's fundamentally what they're advertising.

Not everybody is like this but there are plenty of people in the world who, when they have a problem, are quite motivated to find ways to solve it off their own backs.

Re: LLMs reward expertise

#462

Post by bartread »

massysett wrote: post #438
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…

The whole point is that the friend wouldn’t know what an agent is. The friend would have heard that AI is changing the world and she would have went into ChatGPT or maybe Claude or Gemini. Presuming that the ideal is that anyone should be able to use these tools for anything (which I do not agree with) the chatbot needs to say “you need to use my agent mode.” This is not a wrong tool, wrong job issue. The issue is th…

We're not talking about the friend. I'm talking to the person I responded to: I'm saying they should have recommended a better tool to their friend.

My HR friend found Lovable off her own bat. I imagine she probably Googled or asked ChatGPT something like, "How do I build a website to do BLAH without knowing anything about building websites?"

The point is people talk, they ask questions, they Google, they talk to ChatGPT, and if they have a problem to solve they're often quite motivated to find a solution to that problem off their own backs.

If someone asks me for advice on how to get something built then I'm going to recommend a tool that suits them and their situation, whatever that may be. In this specific situation, if they know nothing about building software, I'm certainly not going to sit them down and have them try to follow the most jank-ass way imaginable of building software with an LLM when I know much better tools exist that are built with people like them in mind.

Seriously, what is with the overly narrow assumptions in the replies I'm getting this morning? You're the third person who's tried to set this same fraying paper tiger on me. Can we all just wake up and think about the issues a bit more in the round, please?

Re: LLMs reward expertise

#463

Post by datenyan »

bartread wrote: post #461
datenyan wrote: post #439

Earlier quoted context omitted.

Isn’t that kinda the point, though? If you already lack the required knowledge to ask a web-based chat UI (which, as an aside, is almost exclusively referring to ChatGPT Free for the average user) to build a HTML page, how could you possibly know to go search for Lovable, let alone figure out agents? I feel as though the gap between the theoretical power of LLMs and what the average user knows of them and their capab…

> how could you possibly know to go search for Lovable, let alone figure out agents? Is this an actually serious question? Am I losing my mind here? I didn't tell my HR friend about Lovable: she found it on her own. Of course someone's not going to Google for Lovable if they've never heard of it, but they might Google for "how do I build a website without knowing anything about it?", or ask ChatGPT the same question.…

> Is this an actually serious question?

Yes, it is. I just Googled that exact question (and I promise I'm not trying to be obstinate when I say I'm Googling the exact phrase!) and it's automated AI response was to use WiX or Squarespace. Prompting it further with "What if I want it to do bespoke things that Squarespace can't do?" it responded with using Figma to design the website UI and then pass it along to either Framer or a "professional developer".

I do genuinely think that this is a discoverability issue. Of course, if you prompt it further with "Could I use AI to do this?" it dutifully responds that it can help with generating HTML, but that's three layers of difficulty to eventually get whatever default model Gemini has for signed-out Google searches to even suggest HTML.

Re: LLMs reward expertise

#464

Post by _joel »

bartread wrote: post #459
_joel wrote: post #440

Earlier quoted context omitted.

Circular dependency detected. You must first know the thing to be able to know the thing.

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.

Re: LLMs reward expertise

#465

Post by bananaflag »

globular-toast wrote: post #447
bananaflag wrote: post #443

Earlier quoted context omitted.

https://chatgpt.com/share/6a60b2eb-0b64-83ee-9c76-7931ca1de0...

Now explain how someone with no expertise would even know about the Dinitz conjecture, or even a conjecture at all for that matter, and how that would be useful to them.

What you are proposing is a barrier no AI and no human and no intelligence would pass.

The idea of an AI that one-shots a task presumes that the one requesting the task already knows what the task is, and no additional expertise.

Similarly, when you ask an AI "please summarize this text" it means you already know what summarization is as a concept.

Re: LLMs reward expertise

#467

Post by algoth1 »

bartread wrote: post #459
_joel wrote: post #440

Earlier quoted context omitted.

Circular dependency detected. You must first know the thing to be able to know the thing.

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.

This: https://xkcd.com/2501/ 1 billion people use chatgpt, but only 10M use codex, which is even more impressive when you consider the chatgpt windows app now comes with codex a click away. This means everything that is super obvious to us, is not for the average person

Re: LLMs reward expertise

#468

Post by nicbou »

WillMorr wrote: post #148
abixb wrote: post #73

The amplifying mirror analogy works best here. LLMs are ultimately a reflection of your own interactions with its weights, the tone you use, the structure with which you construct your prompt, aspects of an issue you tend to focus on, your breadth of vocabulary and world knowledge and whatnot. People who (carefully) use it as an extension of their own mind and senses will very likely thrive, and those who use it as a…

When I get out of my domain, I always ask it to describe things to me "like I'm a senior CS student who doesn't know any industry terms". I find it really easy to skim past the definitions I know and very useful to get the explicit clarification on unfamiliar terminology. Telling it to talk down to you a little also seems to calm down it's tendency to talk like it's trying really hard to convince you it's smart like…

This was part of my system prompt for a while, but the LLM would just make forced, unhelpful CS analogies.

Re: LLMs reward expertise

#469

Post by daishi55 »

JSR_FDED wrote: post #144
daishi55 wrote: post #120

Earlier quoted context omitted.

> All the boring stuff you skipped to get right to the answer you want was just as important This is obviously not the case. There are mountains and mountains of boring, unimportant stuff that LLMs can do for us now. For example, at work I can now make a nestJS dashboard without having any idea what nestJS is. I can just tell the LLM what I want, and it makes it so. This allows me to make my tool useful to people wit…

You’re not the only one who doesn’t know what nestJS is

Yes? My point is that for what I do - low level systems and embedded stuff - nestJS is really not something that I need or want to know about. I just want a good dashboard. Now thanks to LLMs, I can focus on the fun and interesting stuff.

Re: LLMs reward expertise

#470

Post by friendzis »

bartread wrote: post #429
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…

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 touched implementation/deployment ideas and the user has never typed something like "that's enough, how to make this appear in my browser?". While not impossible, the user must have been proactively co-operating (say sidetracked) on not achieving the stated goal.

Post reply on HN