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

451–460 of 606 posts

Re: LLMs reward expertise

#451

Post by tpoacher »

bonsai_spool wrote: post #437
Cthulhu_ wrote: post #405

Earlier quoted context omitted.

Counterpoint, some doctors will zoom in on the most likely problem and misdiagnose. This is in part due to pressure on the health care system (where I live anyway); you can only get a GP appointment for 10 minute blocks, which really isn't a lot. But when a 30-some year old shows up at a rheumatologist with joint pain they will likely go to unusual (at that age) but not unheard of rheumatism/arthritis, not hypermobil…

I think endometriosis is common enough that it would be caught earlier ("Oh, does your joint pain get worse right before you menstruate? Tell me more"), but your point is reasonable. I counter with the platitude that common things are common - especially in fields like primary care, the amount of wasted effort one would expend in pursuing unusual explanations for every presenting symptom is considerable. We thus have…

While this is true as a platitude, I do find that medical colleagues seem to treat this platitude rather overzealously at times, often completely disregarding the posterior probabilities involved. I like to call this the prior-over-posterior fallacy/bias (though one could argue this is simply a variant of the normalcy bias)

E.g., I get the whole "if you hear galloping think horses not zebras" adage, but I guarantee you, if someone comes and says "hey when I was in Africa I saw a black and white striped animal galloping really loud", I bet you an uncomfortably large percentage of the "horses not zebras" crowd would still favour a horse over a zebra diagnosis, despite the overwhelming posterior.

Combine this with our (otherwise reasonable) tendency of avoiding the information bias of seemingly unnecesary tests, and it becomes a big problem, whereby uncommon conditions are treated as common, thereby often escaping detection altogether, and driving down their apparent prior probability even lower, causing a diagnostic vicious cycle.

Re: LLMs reward expertise

#452

Post by NichoPaolucci »

00deadbeef wrote: post #315
RileyJames wrote: post #213

Earlier quoted context omitted.

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.

My non-technical cofounder managed to vibe code a holding page with Claude Design and it walked him through deploying it to Netlify. However for some reason it had him deploy a single HTML file with all the assets encoded as a huge base64 blob in the code that required a massive amount of JavaScript to extract and render.

It's been doing this for our non-technical folk. Giving users a gigantic single file for deployment. We saw one user deploy a JS file with around 3K-5K elements in an array, storing unique IDs of items they wanted to list.

Welcome to Software Development, Lindsey from HR - here's your first database!

People just don't really understand how these things work yet, and they don't know what to ask for, I'm hopeful that they eventually do become more tech-literate, but not sure yet.

Re: LLMs reward expertise

#453

Post by Shorel »

wongarsu wrote: post #368
roncesvalles wrote: post #276

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?

Maybe people don't cite specific apps because they like their jobs, and outing apps as vibe-coded is still seen as negative I personally know of two completely vibe-coded large apps in my professional environment. One by a non-technical manager, made to solve his needs, then sold to customers. Initial development went along great, but by now velocity has greatly slowed down. Also took a lot of engineering hours (of a…

I vibecoded a Postman/Insomnia API tester program, and I use it everyday at work now.

But as another software engineer, I remove myself from that comparison, because the idea is to find out if a non technical person can do the same, that's the definition of vibe coding.

Re: LLMs reward expertise

#454

Post by bonsai_spool »

tpoacher wrote: post #451
bonsai_spool wrote: post #437

Earlier quoted context omitted.

I think endometriosis is common enough that it would be caught earlier ("Oh, does your joint pain get worse right before you menstruate? Tell me more"), but your point is reasonable. I counter with the platitude that common things are common - especially in fields like primary care, the amount of wasted effort one would expend in pursuing unusual explanations for every presenting symptom is considerable. We thus have…

While this is true as a platitude, I do find that medical colleagues seem to treat this platitude rather overzealously at times, often completely disregarding the posterior probabilities involved. I like to call this the prior-over-posterior fallacy/bias (though one could argue this is simply a variant of the normalcy bias) E.g., I get the whole "if you hear galloping think horses not zebras" adage, but I guarantee y…

I hear the complaint, all I can say is that everyone I speak to about this wants to diagnose things correctly while not wasting anybody's time or energy on bad diagnostic workups.

> Combine this with our (otherwise reasonable) tendency of avoiding the information bias of seemingly unnecesary tests

There isn't a way around this: if you order the test and a value is abnormal, you are now committing yourself to treat a thing. We should not be ordering tests if we aren't ready to follow their results to the logical conclusion. So I would disagree that this is a problem in the way you've framed it.

Re: LLMs reward expertise

#455

Post by FiberBundle »

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…

Have you considered the possibility that you're simply not as good as the experts, and that your experience of LLMs being capable of performing your work up to your standards doesn't imply that experts are necessarily in denial?

Re: LLMs reward expertise

#456

Post by Izmaki »

> The most important skill in prompting is expertise in the domain you’re prompting for.

Amen. AI is a tool, a powerful tool indeed, but if you don't know how to apply it, the quality is seriously impacted.

Re: LLMs reward expertise

#457

Post by NichoPaolucci »

0xffff2 wrote: post #340
mettamage wrote: post #300

Earlier quoted context omitted.

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.

I think we desperately need to start differentiating between "is creating" and "has created". I have a couple of "am creating" projects too, but their proximity to "have created" is directly proportional to how much effort and expertise _I_ am bringing, not so much related to the AI's contribution.

I run into this quite a bit. We have users generating MANY apps at our small company (30 FTE), entirely with Claude. It's great to see people mess around and tinker. It's NOT great to see someone with a GH repo that has 750+ commits for what would be MAYBE 1 week of a developers time. SO these are non-developers now spending hours and hours working on software that is probably going to get thrown out.

We're in this spot where we don't know when to cut our losses on projects like this. (Is it even viable as production software? Does it currrently do what it's supposed to, or are they adding new features? Is there a return on continued development efforts?)

None of these apps they have built are seeing any major usage, and I don't think a single one is what I would call "done" (There was a gold rush stage at the beginning of 2026 where senior leadership wanted everyone to spend some time messing around with Claude). Unfortunately, they never told anyone when to stop messing around with Claude, so the ROI is ever diminishing.

Re: LLMs reward expertise

#458

Post by deadpannini »

nvrmndmnm wrote: post #419
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 ran a similar test and got completely different results. My girlfriend (hair stylist/artist) with zero coding background mentioned a Telegram bot idea. I asked "Why not build it yourself?" I gave her a Windows laptop, but she said she wanted what I have instead. So I handed her a USB stick and told her she was on her own now. Fast forward: she now runs Arch Linux with Hyprland (I use Xorg/i3 though), fully riced wi…

Damn you, Poe's law!

Re: LLMs reward expertise

#459

Post by bartread »

_joel wrote: post #440
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…

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.

Re: LLMs reward expertise

#460

Post by lionkor »

nonethewiser wrote: post #99
lionkor wrote: post #70

Earlier quoted context omitted.

This "instant" loop is so fast because it doesn't involve the part where you learn

Learn what? The thing the tool can do instantly? Take the win and spend your energy on bigger problems.

If you don't learn anything, you can be replaced with zero friction
Post reply on HN