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

141–150 of 607 posts

Re: LLMs reward expertise

#141

Post by Greed »

chr15m wrote: post #135
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…

Read the code.

What if the code sucks, because it was vibe coded by an LLM over a dozen disparate sessions?

Re: LLMs reward expertise

#142

Post by gafferongames »

_carbyau_ wrote: post #124
petcat wrote: post #74

Earlier quoted context omitted.

We don't need to learn CSS anymore. Just like we don't need to learn ASM since GCC does a great job generating it from higher-level code.

I just want to point out the exception - the person who the AI learns from. Someone has to know it. And to advance it to the next level requires domain level expertise. Or are we allowing LLM's to determine the next CSS snapshot/version/level/whatever?

Yes

Re: LLMs reward expertise

#143

Post by zeroq »

A good moment to remind everyone that if we took the promise for granted, that AI will in fact prevail and prompting is the one skill that will rule them all... we'll lose all domain experts in one generation.

It's less of "signaling expertise" and more about actually having said "expertise".

In my experience with LLMs it's not uncommon to be having a deep conversation about making pasta, only to be told, after asking for a sample recipe, to get a bucket of paint and a bag of concrete. Of course these hallucinations are way more subtle and easy to miss for someone who doesn't have deep domain knowledge.

Re: LLMs reward expertise

#144

Post by JSR_FDED »

daishi55 wrote: post #120
Jtarii wrote: post #113

Earlier quoted context omitted.

All the boring stuff you skipped to get right to the answer you want was just as important whether you want to admit it or not. Having to read through a structured resource describing something to figure something out has intrinsic value that an LLM is not going to provide you with.

> 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

Re: LLMs reward expertise

#145

Post by a2ff6eeb0 »

JSR_FDED wrote: post #136
a2ff6eeb0 wrote: post #106

Earlier quoted context omitted.

Honestly, we don't really need to learn any more. These days, I mostly copy and paste from tickets to the LLM, and then rubber stamp the output. I have people in my team that try to care about what they're making, but they're generating less code, and filling tickets more slowly, than I am. Even when it comes to system design and architecture, the LLMs aren't great at it, but honestly, they're better than my coworker…

> Honestly, we don't really need to learn any more. Perhaps for your task of closing Jira tickets that’s true - but the you have a decision to make: wait until you’re eliminated or try to anticipate where future competitiveness comes from.

Yeah, that's the thing; future competitiveness isn't going to come from learning, at least not from learning about software. The LLMs have that covered, and software is becoming low status work anyways.

It's largely going to come from interpersonal skills and being likeable enough to be the face of the projects and companies. Technical skill is rapidly dropping in value.

Re: LLMs reward expertise

#146

Post by lagrange77 »

PaulStatezny wrote: post #132
QuercusMax wrote: post #61

Earlier quoted context omitted.

For sure. On a personal coding project I said "I'm a professional software engineer, and while this is a hobby project I'm not just vibe-coding and want to build reliable software" and the agent suddenly started suggesting all kinds of things to make its code more robust.

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.

Re: LLMs reward expertise

#147

Post by zmj »

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…

It's not contradictory to say that expertise is a multiplier, and that models are systematically underconfident in themselves.

Re: LLMs reward expertise

#148

Post by WillMorr »

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 a 8th grader trying to use every single vocab word they learned last week.

Re: LLMs reward expertise

#149

Post by chasd00 »

_carbyau_ wrote: post #124
petcat wrote: post #74

Earlier quoted context omitted.

We don't need to learn CSS anymore. Just like we don't need to learn ASM since GCC does a great job generating it from higher-level code.

I just want to point out the exception - the person who the AI learns from. Someone has to know it. And to advance it to the next level requires domain level expertise. Or are we allowing LLM's to determine the next CSS snapshot/version/level/whatever?

Experts work on gcc so everyone else doesn’t have to.
Post reply on HN