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

571–580 of 607 posts

Re: LLMs reward expertise

#571

Post by swishman »

lowsong wrote: post #569
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…

Your LLM is not "smart" and it cannot "explain", it is a program that can output a statistically average text of an explanation. Don't mistake the capabilities of these models for intelligence.

It explained something to me today. So your point is disproven. What is intelligence then if not explaining things. They can be intelligent without consciousness if that’s what you mean

Re: LLMs reward expertise

#572

Post by lilbigdoot »

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…

This is the only way I've been able to get LLMs to produce code I will actually use. Manually selecting the context for them and asking for a specific piece or similar

I started using harnesses because they are good for when something breaks and it's not trivial to investigate so I'll have the agent tell me what's happening, then using that to produce my own change

Re: LLMs reward expertise

#574

Post by lowsong »

swishman wrote: post #571
lowsong wrote: post #569

Earlier quoted context omitted.

Your LLM is not "smart" and it cannot "explain", it is a program that can output a statistically average text of an explanation. Don't mistake the capabilities of these models for intelligence.

It explained something to me today. So your point is disproven. What is intelligence then if not explaining things. They can be intelligent without consciousness if that’s what you mean

    It explained something to me today. So your point is disproven.
No. It produced a statistically likely answer.

    What is intelligence then if not explaining things.
"the ability to learn, understand, and make judgments or have opinions that are based on reason"[0]

LLMs by definition cannot learn, understand, make judgements, or have opinions. If you find the model to be a tool that is useful to you, by all means. But do not anthropomorphize.

[0] https://dictionary.cambridge.org/dictionary/english/intellig...

Re: LLMs reward expertise

#575

Post by lowsong »

ramraj07 wrote: post #167
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…

The amplifying mirror is not just a characteristic, but the fundamental driving force of LLMs. With every token it consumes, its primary goal is to understand who you are and what you intend. If you type Hola thats sufficient to tell it so much more than if you type hi.

LLMs do not have goals and cannot understand. Please don't anthropomorphize.

Re: LLMs reward expertise

#576

Post by nvrmndmnm »

mikeocool wrote: post #516
nvrmndmnm wrote: post #419

Earlier quoted context omitted.

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…

> mentioned a Telegram bot idea > Fast forward: she now runs Arch Linux with Hyprland (I use Xorg/i3 though), fully riced with cats. Did she end up building the bot or did the LLM just lead her down a desktop Linux rabbit hole?

She did build a bot that saves cooking ideas with a schedule of dates for when to cook what. We have a lot of friends come over, and we cook various dishes for every occasion. Just a couple of days ago, I asked if she had a recipe for a dessert we tried earlier, and she said, "Yes, of course, let me just check that in the bot." The bot that runs locally and still helps with the end goal, makes me feel proud of her, even though that was an experiment she was aware of.

Re: LLMs reward expertise

#577

Post by swishman »

lowsong wrote: post #574
swishman wrote: post #571

Earlier quoted context omitted.

It explained something to me today. So your point is disproven. What is intelligence then if not explaining things. They can be intelligent without consciousness if that’s what you mean

It explained something to me today. So your point is disproven. No. It produced a statistically likely answer. What is intelligence then if not explaining things. "the ability to learn, understand, and make judgments or have opinions that are based on reason"[0] LLMs by definition cannot learn, understand, make judgements, or have opinions. If you find the model to be a tool that is useful to you, by all means. But d…

You're just talking semantics. To me if I read text that helps me understand something, that's an explanation. The black box it comes from is irrelevant.

LLMs do learn, understand, and make judgments. You're just pushing back on the underlying mechanism, which instead of reason/sentience is instead statistics and weights. I'd call that intelligence but I don't really care if you want to call it something else.

Re: LLMs reward expertise

#578

Post by daishi55 »

JSR_FDED wrote: post #473
daishi55 wrote: post #469

Earlier quoted context omitted.

Yes? My point is that for what I do - low level systems and embedded stuff - nestJS is really not something that I need or want to know about. I just want a good dashboard. Now thanks to LLMs, I can focus on the fun and interesting stuff.

My point is that it’s not even called nestJS

Yes it is lol

Re: LLMs reward expertise

#579

Post by lowsong »

swishman wrote: post #577
lowsong wrote: post #574

Earlier quoted context omitted.

It explained something to me today. So your point is disproven. No. It produced a statistically likely answer. What is intelligence then if not explaining things. "the ability to learn, understand, and make judgments or have opinions that are based on reason"[0] LLMs by definition cannot learn, understand, make judgements, or have opinions. If you find the model to be a tool that is useful to you, by all means. But d…

You're just talking semantics. To me if I read text that helps me understand something, that's an explanation. The black box it comes from is irrelevant. LLMs do learn, understand, and make judgments. You're just pushing back on the underlying mechanism, which instead of reason/sentience is instead statistics and weights. I'd call that intelligence but I don't really care if you want to call it something else.

If you believe that an LLM can understand and make judgements then you have fundamentally misunderstood what an LLM is. I'd strongly suggest you read up on the internals.

Re: LLMs reward expertise

#580

Post by zqna »

I'm yet to find a developer who would agree that there is no good git UI, and would like to fix that situation together with me. 90% of those who know what got is dont care. The remaining 10% is split between command line fanatics and those who have no time to spare. One could imagine that 'LLM revolution' would have open the doors to unlimited prototyping but what we instead get is "hey ma i got a different angle at HN comments" at best
Post reply on HN