idf00

It's not to help people train models. It's for end-users to use in an LLM context (like Claude projects or cursor) to help them use your tool better.

If you had python code and you didn't want it to have syntax highlighting or be run/imported or any of the other normal things that you do with python files, it might make sense to have python code in a .txt. file.

Same idea here IMO. .md would signal the wrong intent, as you don't want to render it to markdown formatting or read as a markdown file normally is. You want it to be read as plain unrendered text.

Sam

llms.txt doesn't seem to make it any easier or harder to do that.

Yes. Converting docs to markdown and using them in claude projects, for example, makes a big difference.

What do you have trouble reasoning about regarding FastHTML python compared to Jinja2 or Django templates?

To me, it seems like a direct translation, and that's what makes it easy to reason about. I'm curious about what situations you find more intuitive to use Jinja2 over Python.

For example, in FastHTML:

P() -> <p></p>

Div(P()) -> <div><p></p></div>

The lack of a big transformation layer and things being 1:1 is what makes me think it's just as easy to reason about, but it comes with the advantage of a more powerful Python over a templating language.

I agree that this wouldn't be a great solution if you want people who don't know Python to make HTML edits.

IMO it's not a "structure in one place" vs "more composable so more spread out"

In HTML, you are much more likely to have things in one place because you don't have great options otherwise.

In Python, you can choose to keep things in one place and not compose them, or you can choose to refactor to compose them if that makes them better for your particular use.

It is, however, definitely true that with the extra option, you have the option to refactor it so much it's less readable. How much to refactor and split things apart, decentralize, DRY vs how much to keep things in a structured place can be a hard thing to figure out!

> YouTube instagram and Dropbox definitely don’t scale thanks to python

But python doesn't prevent them from scaling either ;)

> Once you grow beyond the "website" with simple interaction your front end becomes it's own universe

I think this has been a major failing/pain point of web-dev that this MUST be the case. However, I think fastHTML for me is going to fix that. Naturally there is no approach that is ideal in every case, but for a ton of them fastHTML I think works. I've built several things with fastHTML and am very optimistic.

As far as the visual identification, I think python is just as clear to see visual blocks as HTML, but comes with many additional refactoring options (that you can choose when it makes sense to use for your use-case).

Try playing with https://h2x.answer.ai/ and putting in some HTML code and see how it looks in python. Maybe you'll disagree, but I find it quite refreshing.

Quarto supports any language and works just fine. I have quarto blog posts for using APL as an example of a somewhat niche language.

I didn't see anything in the article that indicated the authors believed that those who don't see use cases for LLMs are anti-progress or anti-technology. Is that comment related to the authors of this article, or just a general grievance you have unrelated to this article?

They think they are real business use cases, because real businesses use them to solve their use cases. They know that chatgpt can't solve this off the shelf, because they tried that first and were forced to do more in order to solve their problem.

There's a summary for ya! More details in the stuff that they linked if you want to learn. Technical skills do require a significant time investment to learn, and LLM usage is no different.

Luckily it's not one or the other. You can fine tune and use RAG.

Sometimes RAG is enough. Sometimes fine tuning on top of RAG is better. It depends on the use case. I can't think of any examples where you would want to fine tune and not use rag as well.

Sometimes you fine tune a small model so it performs close to a larger varient on that specific narrow task and you improve inference performance by using a smaller model.

FYI this course does cover a lot of intuitive understanding of techniques, but it also does cover this theory. Everything is done from the foundation level, and all of the stuff you mentioned is taught and implemented from scratch as part of the course.

Of course there's loads more to do on gaining intuition, and loads more theory to be learned once the course is done! Only so much can fit in a single course :)

Deep Learning from the Foundations IS part 2. They are not talking about how part 1 starts. They are talking about how part 2 starts. This mirrors how their book is written, with the content typically in Deep Learning for Foundations being the second half of the book. I've taken the courses every year, it's always been like that.

You should consider taking a look at part 1 of the course if you want to understand the starting curriculum: https://course.fast.ai/

> I haven't taken the course, but that sounds like a horrible place to start a course on understanding deep learning.

Sounds like you support the course author's decision to make this part 2 of the course series to be taken after part 1 is completed!

I think co-writing and co-teaching a math course at a deep learning company he co-founded, pinning that to the github repo and moving it close to the top of the home page makes it pretty clear he does see value in math in deep learning. I mean, if you need other evidence beyond than the fact that he teaches math needed to understand and build things from scratch in the deep learning course...

In the courses he has always been clear you don't need a ton of math to begin. He's also always been clear that as you progress you will encounter math that you need to learn to continue. He's always clear that that is ok if you don't know it before you start and it's ok to learn it when you need it.

Fantastic course - Fastai courses are a must for anyone looking to learn Deep Learning/ML.

If you knew him at all or had bothered to spend the time to look at his work and projects in any level of depth, you would know he is not a self-aggrandizing person.

And if the arguement is that this is a gateway action that leads to other bad things, that's not an arguement I put any stock in. It's used a lot in many places and many discussions, but just focus calling out the bad. It isn't his responsibility to ensure that some person building off his work at some point in the future does the appropriate level of research appropriate for their project. Assuming that an action is bad because you think someday down the road it might lead someone else to do something and that that something will be a bad thing is just ridiculous.

Why are people nitpicking about this? So the term/phrase he came up with was so descriptive that other people had also thought of the same term previously. He didn't steal anyones research on the topic, or steal code for the project, or deny credit to a developer working on a project. It's 2 simple words that are extremely common in the english language. Of course lots of people have happened to put them together before.

This is my second time on hacker news, and I don't think I will be back. Why not offer to help the project, or show support? Why try to find something to fight about? It's just demoralizing to see the lack of kindness from people.