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

Nerd: A language for LLMs, not humans

nerd-lang.org

Post reply on HN
Print view View original

71–80 of 110 posts

Re: Nerd: A language for LLMs, not humans

#71

Post by alienbaby »

sublinear wrote: post #69
wilsonnb3 wrote: post #27

Earlier quoted context omitted.

> "Why is Claude writing TypeScript I'm supposed to read?" 40% of code is now machine-written. That number's only going up. How much of the code is read by humans, though? I think using languages that LLMs work well with, like TS or Python, makes a lot of sense but the chosen language still needs to be readable by humans.

Why do people keep saying LLMs work well with high level scripting languages? I've never had a good result. Just tons of silent bugs that are obvious those experienced with Python, JS/TS, etc. and subtle to everyone else.

Perhaps they are being more successful in their use of llm's than you are?

Re: Nerd: A language for LLMs, not humans

#72

Post by alienbaby »

diath wrote: post #49

The entire point of LLM-assisted development is to audit the code generated by AI and to further instruct it to either improve it or instruct it to fix the shortcomings - kind of being a senior dev doing a code review on your colleague's merge request. In fact, as developers, we usually read code more than we write it, which is also why you should prefer simple and verbose code over clever code in large codebases. Th…

This describes where we are at now. I don't think it's the entire point. I think the point is to get it writing code at a level and quantity it just becomes better and more efficient to let it do its thing and handle problems discovered at runtime.

Re: Nerd: A language for LLMs, not humans

#74

Post by sublinear »

throwaway150 wrote: post #42
torben-friis wrote: post #26

>NERD is what source code becomes when humans stop pretending they need to write it. It is so annoying to realise mid read that a piece of text was written by an LLM. It’s the same feeling as bothering to answer a call to hear a spam recording.

I don't know how you can be so sure about that sentence being written by LLM. I can imagine it is perfectly possible that a human could've written that. I mean, on some day I might write a sentence just like that. I think HN should really ban complaints about LLM written text. It is annoying at best and a discouraging insinuation at worst. The insinuation is really offensive when the insinuation is false and the auth…

[dead]

Re: Nerd: A language for LLMs, not humans

#76

Post by sublinear »

alienbaby wrote: post #71
sublinear wrote: post #69

Earlier quoted context omitted.

Why do people keep saying LLMs work well with high level scripting languages? I've never had a good result. Just tons of silent bugs that are obvious those experienced with Python, JS/TS, etc. and subtle to everyone else.

Perhaps they are being more successful in their use of llm's than you are?

Yes "success" as they understand it, and they are always so smug while refusing to show or even discuss the code the LLM produced.

A poor craftsman may blame his tools, but some tools really are the wrong ones for the job.

Re: Nerd: A language for LLMs, not humans

#77

Post by lovidico »

How can a language both be human-unfriendly and also sanely auditable? The types of issues that require human intervention in LLM output are overwhelmingly things where the LLM depends on the human to detect things it cannot. Seems to break the loop if the human can’t understand well

Re: Nerd: A language for LLMs, not humans

#78

Post by ksec »

Edited for Formatting.

My take on the timeline; ( Roughly I think some of them are in between but may be best not to be picky about it )

1950s: Machine code

1960s: Assembly

1970s: C

1980s: C++

1990s: Java

2000s: Perl / PHP / Python / Ruby

2010s: Javascripts / Frameworks

2020s: AI writes, humans review

But the idea is quite clear once we have written this out, we are moving to higher level abstraction every 10 years. In essence we are moving to Low Code / No Code direction.

The languages for AI assisted programming idea isn't new. I have heard at least a few said may be this will help Ruby ( Or Nim ) . Or a Programming languages that is closest reassembling of the English language.

And considering we are reading the code more that ever writing it, since we are mostly reviewing now with LLM. I am thinking if this will also changes the pattern or code output preference.

I think we are in a whole different era now. And a lot of old assumptions we have about PL may need a rethink. Would Procedure Programming and Pascal made a comeback, or the resurgence of SmallTalk OO Programming ?

Re: Nerd: A language for LLMs, not humans

#79

Post by lovidico »

tyushk wrote: post #66
norir wrote: post #41

Earlier quoted context omitted.

I suspect this is wrong. If you are correct, that implies to me that LLMs are not intelligent and just are exceptionally well tuned to echo back their training data. It makes no sense to me that a superior intelligence would be unable to trivially learn a new language syntax and apply its semantic knowledge to the new syntax. So I believe that either LLMs will improve to the point that they will easily pick up a new…

I don't think your ultimatum holds. Even assuming LLMs are capable of learning beyond their training data, that just lead back to the purpose of practice in education. Even if you provide a full, unambiguous language spec to a model, and the model were capable of intelligently understanding it, should you expect its performance with your new language to match the petabytes of Python "practice" a model comes with?

Further to this, you can trivially observe two further LLM weaknesses: 1. that LLMs are bad at weird syntax even with a complete description. E.g. writing StandardML and similar languages, or any esolangs. 2. Even with lots of training data, LLMs cannot generalise their output to a shape that doesn’t resemble their training. E.g. ask the LLM to write any nontrivial assembler code like an OS bootstrap.

LLMs aren’t a “superior intelligence” because every abstract concept they “learn” is done so emergently. They understand programming concepts within the scope of languages and tasks that easily map back to those things, and due to finite quantisation they can’t generalise those concepts from first principles. I.e. it can map python to programming concepts, but it can’t map programming concepts to an esoteric language with any amount of reliability. Try doing some prompting and this becomes agonisingly apparent!

Re: Nerd: A language for LLMs, not humans

#80

Post by legostormtroopr »

norir wrote: post #41
nrhrjrjrjtntbt wrote: post #20

Feels like a dead end optimisation ala the bitter lesson. No LLM has seen enough of this language vs. python and context is now going to be mostly wordy not codey (e.g. docs, specs etc.)

I suspect this is wrong. If you are correct, that implies to me that LLMs are not intelligent and just are exceptionally well tuned to echo back their training data. It makes no sense to me that a superior intelligence would be unable to trivially learn a new language syntax and apply its semantic knowledge to the new syntax. So I believe that either LLMs will improve to the point that they will easily pick up a new…

> If you are correct, that implies to me that LLMs are not intelligent and just are exceptionally well tuned to echo back their training data.

Yes.

This is exactly how LLMs work. For a given input, an LLM will output a non-deterministic response that approximates its training data.

LLMs aren’t intelligent. And it isn’t that they don’t learn, they literally cannot learn from their experience in real time.

Post reply on HN