Rendered at 22:24:51 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
aleph_minus_one 2 hours ago [-]
> Dynamically typed languages generally have a lower LLM token cost than traditional statically typed languages because omitting explicit type declarations makes the code more compact.
If this was true, the programming languages that are very much on the left side of
should be very ideal for LLMs, in particular if they are dynamically typed.
What I can tell you is: I experimented with AI prompts for generating Wolfram (Mathematica) code using some LLMs, and I can tell you that the results were very disappointing: in my experience LLMs have difficulties with programming languages that are
- very concise, and
- for which there is less code publicly available.
Wolfram (Mathematica) is a good example of such a programming language.
JoeyJoJoJr 4 minutes ago [-]
I’ve actually found Sol delivers great results with Odin, despite there not being much Odin code available. I think it is able to work well with it because:
- It is a rather simple language
- It has a lot of very useful libraries already built in.
With just a single main.odin file you can do a heck of a lot stuff, which LLMs seem to like.
nylonstrung 2 hours ago [-]
One thing worth noting is that syntactic density doesn't necessarily mean cheaper because because symbols don't chunk/tokenize as well as plain English
What I see from results like this is that the delta between languages is small enough now that it's hard to justify not not using something like Rust for the performance and correctness benefits if you're using LLMs and it fits the domain
_doctor_love 3 hours ago [-]
I love Dan's writing. I really do. But I don't understand why he doesn't have some basic styling on his blog so that it's easier to read.
scared_together 21 minutes ago [-]
It may be an artistic/engineering choice to demonstrate what minimizing bloat to an extreme degree looks like.
I love this take because I had exactly the opposite idea. I thought the combo of remarkably simple text (not even wrapped) with incredible, full width visualizations was chef's kiss. I really like the balance there personally, but I hear you. Does your browser have Reader Mode or something like that? I don't use those tools personally, but I believe they will recast the text parts into something that renders optimally for reading (ideal font size, number of characters per line, etc....).
9rx 3 hours ago [-]
Users being able to supply their own stylesheet is a core tenant of CSS. Go nuts and make it look however your heart desires!
_doctor_love 2 hours ago [-]
Supply my own stylesheet? No thank you, I'm not here to do work for free.
9rx 2 hours ago [-]
Is doing something for yourself really working for free? That's an interesting take. But I can understand why you don't want this for yourself, so enjoy the page in all its splendour as it is already!
_doctor_love 1 hours ago [-]
So every person who reads Dan's blog and finds the layout too dense, they should write and maintain a stylesheet for his site?
And every person globally should do this as well for any other website that doesn't have a good default reading experience?
If this was true, the programming languages that are very much on the left side of
> https://danuker.go.ro/programming-languages.html#non-math-ma...
> https://danuker.go.ro/programming-languages.html#overall-map
should be very ideal for LLMs, in particular if they are dynamically typed.
What I can tell you is: I experimented with AI prompts for generating Wolfram (Mathematica) code using some LLMs, and I can tell you that the results were very disappointing: in my experience LLMs have difficulties with programming languages that are
- very concise, and
- for which there is less code publicly available.
Wolfram (Mathematica) is a good example of such a programming language.
- It is a rather simple language - It has a lot of very useful libraries already built in.
With just a single main.odin file you can do a heck of a lot stuff, which LLMs seem to like.
What I see from results like this is that the delta between languages is small enough now that it's hard to justify not not using something like Rust for the performance and correctness benefits if you're using LLMs and it fits the domain
https://danluu.com/web-bloat/
And every person globally should do this as well for any other website that doesn't have a good default reading experience?