Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

LLMs as the new high level language

federicopereiro.com

Post reply on HN
Print view View original

161–170 of 396 posts

Re: LLMs as the new high level language

#161

Post by pavlov »

PunchyHamster wrote: post #156

At this point I'm just waiting for people claiming they managed team of 20 people, where "20 people" were LLMs being fed a prompt

This claim has been going around for a while.

I know someone who has been spending $7k / month on Cursor tokens for the past six months, managing such a team of agents… But curiously the results seem to be endless PDF-ware, and every month there’s a new reason why the project is not yet quite ready to be used on real data.

LLMs are very good at making you think they’re giving you what you hoped to get.

Re: LLMs as the new high level language

#163

Post by mjr00 »

hackyhacky wrote: post #157
mjr00 wrote: post #120

Earlier quoted context omitted.

I put myself in the shoes of the burger restaurant owner. I vibe coded a website. Sweet. I talk to my cousin who's doing the web hosting and he says he can't host a "Pee Haich Pee" site. I don't know what that is. Suddenly the thing that didn't matter actually really fucking matters This is like saying it doesn't matter if your pipes are iron, lead or PVC because you don't see them. They all move water and shit where…

> I talk to my cousin who's doing the web hosting and he says he can't host a "Pee Haich Pee" site I already addressed this exact argument in another comment. In short: hosting is an implementation detail. The LLM can solve this problem just like any coding bug. The user can give his cousin's email to the LLM, which will solve the issue by finding better hosting, rewriting the program in another language, or using Do…

> The user can give his cousin's email to the LLM, which will solve the issue by finding better hosting, rewriting the program in another language, or using Docker.

Can you please point to a currently available LLM that can do this?

Re: LLMs as the new high level language

#164

Post by cortesoft »

lpnam0201 wrote: post #117
cortesoft wrote: post #111

Earlier quoted context omitted.

> PureScript is a programming language. English is not. Why can’t English be a programming language? You would absolutely be able to describe a program in English well enough that it would unambiguously be able to instruct a person on the exact program to write. If it can do that, why couldn’t it be used to tell a computer exactly what program to write?

English can be ambiguous. Programming languages like C or Java cannot

English CAN be ambiguous, but it doesn't have to be.

Think about it. Human beings are able to work out ambiguity when it arrises between people with enough time and dedication, and how do they do it? They use English (or another equivalent human language). With enough back and forth, clarifying questions, or enough specificity in the words you choose, you can resolve any ambiguity.

Or, think about it this way. In order for the ambiguity to be a problem, there would have to exist an ambiguity that could not be removed with more English words. Can you think of any example of ambiguous language, where you are unable to describe and eliminate the ambiguity only using English words?

Re: LLMs as the new high level language

#165

Post by geon »

cortesoft wrote: post #111
WoodenChair wrote: post #103

Earlier quoted context omitted.

PureScript is a programming language. English is not. A better analogy would be what would you say about someone who uses a No Code solution that behind the scenes writes Java. I would say that's a much better analogy. NoCode -> Java is similar to LLM -> Java. I'm not debating whether LLMs are amazing tools or whether they change programming. Clearly both are true. I'm debating whether people are using accurate analo…

> PureScript is a programming language. English is not. Why can’t English be a programming language? You would absolutely be able to describe a program in English well enough that it would unambiguously be able to instruct a person on the exact program to write. If it can do that, why couldn’t it be used to tell a computer exactly what program to write?

No. Natural language is vague, ambiguous and indirect.

Watch these poor children struggle with writing instructions for making a sandwich:

https://youtu.be/FN2RM-CHkuI

Re: LLMs as the new high level language

#166

Post by zkmon »

abcde666777 wrote: post #130

Are these kinds of articles a new breed of rage bait? They keep ending up on the front page with thriving comment sections, but in terms of content they're pretty low in nutritional value. So I'm guessing they just rise because they spark a debate?

> So I'm guessing they just rise because they spark a debate?

Precisely. Attention economy. It rules.

Re: LLMs as the new high level language

#168

Post by anoplus »

sph wrote: post #143
anoplus wrote: post #138

Earlier quoted context omitted.

I am interested in a post that will teach me how to consume only the news that really relevant for me

Here’s one: just don’t read the news. Google what you are interested in at the moment, and dive long into what matters to you, rather than being fed engagement bait. Easier said than done, I understand that.

I guess I'll have an agent for that one day. News agent.

Re: LLMs as the new high level language

#169

Post by fragmede »

rezonant wrote: post #121
ChrisGreenHeur wrote: post #89

Earlier quoted context omitted.

I may have bad news for you on how compilers typically work.

You'll need to share with the class because compilers are pretty damn deterministic.

Only mostly, and only relatively recently. The first compiler is generally attributed to Grace Hopper in 1952. 2013 is when Debian kicked off their program to do bit-for-bit reproducible builds. Thirteen years later, Nixos can maybe produce bit-for-bit identical builds if you treat her really well. We don't look into the details because it just works and we trust it to work, but because computers are all distributed systems these days, getting a bit-for-bit identical build out of the compiler is actually freaking hard. We just trust them to work well enough (and they do), but they've had three fourths of a century to get there.
Post reply on HN