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

321–330 of 605 posts

Re: LLMs reward expertise

#321

Post by kkoncevicius »

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…

This was true some time ago but nowadays I don't get this impression. Seems like whatever style I type in, the LLM is already pre-prompted to respond in "its" "own" "style".

Re: LLMs reward expertise

#322

Post by xlii »

I consider myself senior engineer. When talking with junior colleagues they often are surprised how little I care about some things and how much I care about others.

These internal "attention weights" are highly influential parameters of how I work with LLM.

E.g. when working with Rust I often hold strict control over structures and lifetimes. But when lately I've been doing token-based bind generation I didn't care about anything outside of high level patterns like RAII and ultimately - API ergonomics which was verified in consumer app.

I've been in position of porting real-code to vibe-code platform and seeing non-technical people prompt-stream (they were shared across accounts) I know why they engaged engineer to run this work.

Their efforts took 6 weeks, I ported app within 4 days and (to be honest with myself) without LLM I that'd be 3M+ work pre-LLM.

In short: I observed same effect as claimed.

Re: LLMs reward expertise

#323

Post by harvey9 »

raincole wrote: post #313
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…

Do your friend at least know what Claude Code (or any harness) is? Of course she wouldn't be able to make a website if she doesn't even know the right tools to use. But I don't think it prove anything. Knowing and installing Claude Code might not be a common sense, but nor is it "expertise" or "skill." I've seen in first hand that people struggle installing Steam . Yes, "people" in the plural. But just because some p…

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.

Re: LLMs reward expertise

#324

Post by knowaveragejoe »

DaiPlusPlus wrote: post #226
HoneySpoons wrote: post #217

Earlier quoted context omitted.

ELI5 is the way to go. I have Claude break down high level physics "as if I'm a farmer standing in a field" - works beautifully.

> I have Claude break down high level physics "as if I'm a farmer standing in a field" - works beautifully. Careful now: https://www.youtube.com/watch?v=TMoz3gSXBcY

There's an irony here in using Gemini to summarize this 40 minute video right from the page.

Re: LLMs reward expertise

#325

Post by petesergeant »

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 had the absolute opposite experience with a friend of mine. I started by setting her up with a terminal emulator on the web linked to Claude Code, and written a CLAUDE.md that told it how to deploy. These days (with no further intervention by me) she’s running Claude Code natively on her laptop, and she tagged me yesterday on Facebook in some update about how much more she enjoyed using Claude Code than plain Claude.

Re: LLMs reward expertise

#326

Post by jagenabler2 »

defgeneric wrote: post #250
postalcoder wrote: post #4

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…

Did you maybe consider that the 10 year timeline is not denial, but actually well educated reasoning based on Yuval’s experience and understanding of the problem space? You shouldn’t dismiss people’s thoughts as denial just because they don’t match your perspective.

Re: LLMs reward expertise

#327

Post by harvey9 »

sam_lowry_ wrote: post #312
ElectricalUnion wrote: post #218

Earlier quoted context omitted.

> 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.

I am old enough to have observed non-tech workers using all kinds of text-based interfaces and it was a real pleasure seeing how old ma's would jiggle numbers on the bc-style TUI in the way that would offset any modern CompSci major.

Me too. But did you see them on their first day using it or their thousandth?

(Also you don't need to be that old. Less than 10 years ago I watched a doctor breeze through some clinical system while I was crawling along constantly referring to the manual)

Re: LLMs reward expertise

#328

Post by imhoguy »

RileyJames wrote: post #213
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’d love to see this experiment executed with Claude design. Particularly with something static, I don’t think they’d fail to get a result. But without domain knowledge I think they’d misunderstand prototype with finished product. Without knowing what it’s doing, it’s hard to know what it’s not doing.

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 extract part of app into Design, let it even use playwright-cli to get full rendering of the particular view.

- perform design session in Design.

- once design system is perfected I go down to Claude Code dungeons, do /design-sync.

- perform on the stack implementation session.

Actually you don't need Claude Design UI for any of that too. Just ask any coding agent to prepare local mock HTMLs and iterate over them.

Re: LLMs reward expertise

#329

Post by Melatonic »

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…

Reminds me of watching someone who has no idea how to use a search engine try to use a search engine

Re: LLMs reward expertise

#330

Post by vector_spaces »

harvey9 wrote: post #323
raincole wrote: post #313

Earlier quoted context omitted.

Do your friend at least know what Claude Code (or any harness) is? Of course she wouldn't be able to make a website if she doesn't even know the right tools to use. But I don't think it prove anything. Knowing and installing Claude Code might not be a common sense, but nor is it "expertise" or "skill." I've seen in first hand that people struggle installing Steam . Yes, "people" in the plural. But just because some p…

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 alone Claude Code.
Post reply on HN