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

221–230 of 607 posts

Re: LLMs reward expertise

#221

Post by paulhebert »

dhbradshaw wrote: post #166
dbalatero wrote: post #126

> Of course both are useful, but I’d rather have familiarity with the codebase than a deep general understanding of software systems. In my experience, getting that familiarity with a particular codebase in a way that isn't surface-level has always been a hands-on process. E.g. just because I know many general things about software, I need to know the particulars of the current codebase I'm in to know what is reasona…

I think this is only a partial answer but I've been surprised by how familiar dev leads become with the app even if they are not in the code. They tend to stick around and they engage in the problem solving on a higher level and develop a detailed picture of how the app does and should behave. So at least that part of the expertise may come from working with an LLM to solve problems.

They also review a huge amount of the code changes and rubber duck/plan/troubleshoot a lot

Re: LLMs reward expertise

#222

Post by dmazzoni »

matthew-wegner wrote: post #192
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…

Are you describing a "chat window" experience here? This is apples to oranges.

As opposed to what?

If you ask a non-programmer to install Claude Code, just installing it will be a challenge, then opening the shell and interacting with it. Things as simple as copying and pasting can present roadblocks if you've never used a shell before, and things intuitive to programmers like using up-arrow to go back to a previous prompt would never occur to someone in the field.

Claude Code seems so simple and natural of a UI to programmers, it's easy to forget how much it builds on.

Re: LLMs reward expertise

#223

Post by ElectricalUnion »

akoboldfrying wrote: post #215
matthew-wegner wrote: post #192

Earlier quoted context omitted.

Are you describing a "chat window" experience here? This is apples to oranges.

Not really, for making a single-file anything ex nihilo. I suppose the chat window won't be able to run a linter or make and run tests as a typical "eager" agent might, so maybe it will make more mistakes.

Almost all web chatbot providers have code sandboxes that they will run (limited) tooling for you. If you ask for it, it will run deterministic linters, formatters, format converters, tests for you. Older versions of Claude would for example happily try to reverse engineer entire artifacts for you, once you provide a URL.

Re: LLMs reward expertise

#224

Post by lowbloodsugar »

uzername wrote: post #203

At work we call this implicit steering. To use webdev metaphor, if a non-technical person describes making a web page with a big block at the top and some things to click on and then my pictures below that, that will eventually get somewhere. Meanwhile, if you know industry jargon, you might describe a hero, with call to action buttons, and then below a 3x3 grid of images of my portfolio photos—that's likely going to…

Opus, assume i know nothing about web development. if i wanted to design a new webpage, with a good design, what are some of the terms of art, some best practices? Like if i wanted a big block at the top, some things to click on and some pictures below that, is there terminology for that?

>Yes. Nearly everything you described has a standard name. Here is the vocabulary, organized by what part of the page it describes...

Goes on to identify Header, Navbar, Stucky header, hamburger menu, hero, CTA, Above the fold etc.

>So your described page is: header/nav -> hero with CTA -> card grid -> footer. That is the single most common landing page structure in existence, and that is fine. Being conventional is a feature, not a failure.

I've had the same conversation with an electrician wiring a car charger: we are more likely to succeed if I use his terminology.

Re: LLMs reward expertise

#225

Post by unpwn »

StevePrefontain wrote: post #172
dbalatero wrote: post #126

> Of course both are useful, but I’d rather have familiarity with the codebase than a deep general understanding of software systems. In my experience, getting that familiarity with a particular codebase in a way that isn't surface-level has always been a hands-on process. E.g. just because I know many general things about software, I need to know the particulars of the current codebase I'm in to know what is reasona…

We are having trouble onboarding engineers with AI now. Some still struggle after their first year with very basic concepts/patterns we use and make the same mistakes again and again in their PRs because they just ask Claude to fix it and never internalize it. I think using LLMs feels good at first because you can get tickets out the door faster but you never develop enough knowledge to make a big impact or become an…

Honestly you should probably invest in baking the basic patterns and concepts of your codebase into shared skills that are applied to everyone's Claude sessions.

Re: LLMs reward expertise

#226

Post by DaiPlusPlus »

HoneySpoons wrote: post #217
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…

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

Re: LLMs reward expertise

#227

Post by DaiPlusPlus »

Avicebron wrote: post #184
japhib wrote: post #182

Earlier quoted context omitted.

A punchy tricolon containing 2 analogies that don’t quite make sense. That’s some S-tier AI-mimicking. Nice!

One could say that it being an LLMism is...load-bearing :)

Here's the kicker: it's not just load-bearing — it's a whole new paradigm support column.

Re: LLMs reward expertise

#228

Post by jaggederest »

jerf wrote: post #163
WillMorr wrote: post #148

Earlier quoted context omitted.

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…

I've been using a prompt that comes from the opposite direction for non-programming stuff: "Assume the user is an expert in all fields; while this is clearly logically untrue on a literal level, the user prefers to see a field's technical terminology and then ask the AI about terms the user does not understand rather than get an inaccurate statement about some issue." Whether you have to reassure the LLM that this is…

Off topic, but stretching is absolutely useless for ... stretching. And vital for retaining and enhancing usable range of motion (not static stretching, still, but dynamic stretching / mobility under tension).

The wildest thing is, there's no evidence that I can find that static stretching does... anything? It increases pain tolerance through the range of motion, but not any more than just asking people to try harder etc. And it doesn't build up, so after you stretch once for a given day, you're done.

Edit: after looking into it a bit further there's actually a cochrane review that stretching does bupkis, fascinating. It's also the first "Good" evidence graded cochrane review I've seen.

Re: LLMs reward expertise

#229

Post by kibwen »

nonethewiser wrote: post #97
kibwen wrote: post #78

Earlier quoted context omitted.

I want to believe this is sarcasm, but it's so hard to tell these days.

For many cases like the one described, its true.

It's not. The majority of people regularly using GCC to develop C code (IOW, the primary use case of GCC) are familiar with assembly.

Re: LLMs reward expertise

#230

Post by wilg »

dmazzoni wrote: post #222
matthew-wegner wrote: post #192

Earlier quoted context omitted.

Are you describing a "chat window" experience here? This is apples to oranges.

As opposed to what? If you ask a non-programmer to install Claude Code, just installing it will be a challenge, then opening the shell and interacting with it. Things as simple as copying and pasting can present roadblocks if you've never used a shell before, and things intuitive to programmers like using up-arrow to go back to a previous prompt would never occur to someone in the field. Claude Code seems so simple a…

The terminal? No way, the normal Claude or ChatGPT desktop app.
Post reply on HN