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

401–410 of 606 posts

Re: LLMs reward expertise

#401

Post by sam_lowry_ »

ben_w wrote: post #392
sam_lowry_ wrote: post #314

Earlier quoted context omitted.

Scary but then liberating once you get to know what you have to type in to reach your objective.

Yeah, if you're willing to put in that much effort. I started on this path literally about as soon as I could read thanks to the family having bought a Commodore 64 for my older siblings, but also perfect timing in that when I got to this age the sibling whose room it was in had just gone off to university. Most people are not like this, in much the same way that they're not going to read the T&C end-to-end (another…

What an ode to exceptionalism /s

You also think that you are smarter than the people flooding Ceuta streets these days, don't you?

Re: LLMs reward expertise

#402

Post by bananaflag »

Every thing passes through the following stages:

1. AI cannot do something.

2. AI starts being able to do something, but one needs to prompt it carefully, so one needs to be an expert, see, we will always need human experts 3. AI just one-shots it.

Why do people still need to say this for each and every task? It's just reliving the bitter lesson over and over again.

Re: LLMs reward expertise

#403

Post by ChrisMarshallNY »

roncesvalles wrote: post #351
downloadram wrote: post #338

Earlier quoted context omitted.

>she didn’t find a way to tip the AI into “just do it, write it now” mode worse, the longer an LLM conversation goes on, but especially with constricted/free models (yes the simple chat interface they are likely using) the harder it is to get an LLM into this mode even *IF* you know the right words to say at that point the best way forward is to terminate the exchange entirely, and to start off with the right initial…

Also, the correct way to LLM is to constantly trial-and-error in new/branched contexts. Remember the LLM is not a human employee. You don't have to say "yes and" to whatever crap they produced so as to not hurt their feelings or infringe upon their creative autonomy, nor do you have to defend the correctness of your original instructions so that they don't think less of you for asking them to chase the wrong goose. I…

> The only way I can maintain my pace of branched trial-and-error is by using claude.ai/chat and manually extricating code fragments to and from my codebase. The human is still the best harness for production-level code.

That’s been the way I do it.

I suppose that it will be considered “quaint,” soon enough, but I have found it to be effective.

Re: LLMs reward expertise

#404

Post by manojbajaj95 »

I agree with the premise that LLMs reward experstise, but people without expertise can very eaily learn to prompt correctly and get to a result that is very good. I remember somebody proved a mathematical conjecture by just asking 'keep going' in plain english without a mathematics background.

Re: LLMs reward expertise

#405

Post by Cthulhu_ »

tpoacher wrote: post #376

Both the article and some of the discussions here share a lot of commonalities with doctors taking a medical history. There is a certain skill in guiding the conversation towards useful outputs, while not dictating the exact outputs to a patient who is eager to please with their responses. E.g., medical history taking protocol always says to start with open ended (albeit structured) questions, and converge towards mo…

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 hypermobile spectrum disorder. When a woman goes to a GP with period pain they will be prescribed mild pain killers or anticonception pills and fobbed off, until a decade and much suffering / many more issues later they get diagnosed with endometriosis.

Re: LLMs reward expertise

#406

Post by swiftcoder »

sans_souse wrote: post #353
sam_lowry_ wrote: post #305

Earlier quoted context omitted.

Harness? I am an avid HN reader but even I don't yet fully understand how this word is used in the AI context. Which is exactly the point of the OP. It all boils down to naming things and cache invalidation, /s

My question is do we harness a bootstrap or bootstrap a harness?

You strap your harness to your bootstraps, and then you can pull yourself up by your own bootstraps... right?

Re: LLMs reward expertise

#407

Post by whosdat »

Sure. Not to speak about the ones who own the LLMs.

They just rewarded with a FREE SUBSCRIPTION one hundred thousands or so professional mathematicians! Undoubtedly, to advance mathematics! Hurrah!

Re: LLMs reward expertise

#408

Post by FinnLobsien »

manojbajaj95 wrote: post #404

I agree with the premise that LLMs reward experstise, but people without expertise can very eaily learn to prompt correctly and get to a result that is very good. I remember somebody proved a mathematical conjecture by just asking 'keep going' in plain english without a mathematics background.

But then what's the point of the proof? I guess it's cool that it's possible, but given enough tokens, you could take someone who's never written a line of code and have them prompt AI to turn their vibe-coded meal prep app into a highly available distributed system with multi-region failover and immutable audit logs.

They would probably get something that checks those boxes in one way or another, but what does it do for them?

Re: LLMs reward expertise

#409

Post by vdanielpop »

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…

I am really curious about that skill now, would you mind sharing it?

Re: LLMs reward expertise

#410

Post by FinnLobsien »

I think this is extremely true when it comes to prompting, but not only in this way. I would add that this also applies to an LLM's output on deep enough topics.

Anyone can point at a public GitHub repo and have an LLM write the documentation for it. Whether that documentation is good requires understanding that codebase.

There's no way around expertise unless we're talking about strictly mechanical tasks.

I do think LLMs are incredible at helping to build your expertise. You could point it at a codebase and say: "Explain how this API works" and interrogating the LLM until you get an explanation at exactly your level of understanding.

Post reply on HN