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

Minifying HTML for GPT-4o: Remove all the HTML tags

blancas.io

Post reply on HN
Print view View original

31–40 of 52 posts

Re: Minifying HTML for GPT-4o: Remove all the HTML tags

#31

Post by zaptrem »

throwup238 wrote: post #4

I don't think that Mercury Prize table is a representative example because each column has an obviously unique structure that the LLM can key in on: (year) (Single Artist/Album pair) (List of Artist/Album pairs) (image) (citation link) I think a much better test would be something like "List of elements by atomic properties" [1] that has a lot of adjacent numbers in a similar range and overlapping first/last column t…

LLMs are trained on Wikipedia (and, since it's high quality open license data, probably repeatedly), so this test is contaminated.

Re: Minifying HTML for GPT-4o: Remove all the HTML tags

#35

Post by audessuscest »

coddle-hark wrote: post #29

Anecdotally, the same seems to apply to the output format as well. I’ve seen much better performance when instructing the model to output something like this: name=john,age=23 name=anna,age=26 Rather than this: { matches: [ { name: "john", age: 23 }, { name: "anna", age: 26 } ] }

markdown works better than json too

Re: Minifying HTML for GPT-4o: Remove all the HTML tags

#36

Post by wis »

bearjaws wrote: post #21
cpursley wrote: post #19

What I do is convert to markdown, that way you still get some semantic structure. Even built an Elixir library for this: https://github.com/agoodway/html2markdown

Seems to be the most common method I've seen, it makes sense given how well LLMs understand markdown.

Why do LLMs understand markdown really well? (besides the simple, terse and readable syntax of markdown)

They say "LLMs are trained on the web", are the web pages converted from HTML into markdown before being fed into training?

Re: Minifying HTML for GPT-4o: Remove all the HTML tags

#37

Post by Shadowmist »

beepbooptheory wrote: post #17

You step back and realize: we are thinking about how to best remove some symbols from documents that not a moment ago we were deciding certainly needed to be in there, all to feed a certain kind of symbol machine which has seen all the symbols before anyway, all so we don't pay as much cents for the symbols we know or think we need. If I was not a human but some other kind of being suspended above this situation, wit…

It’s all one big piece of tape.

Re: Minifying HTML for GPT-4o: Remove all the HTML tags

#38

Post by nprateem »

wis wrote: post #36
bearjaws wrote: post #21

Earlier quoted context omitted.

Seems to be the most common method I've seen, it makes sense given how well LLMs understand markdown.

Why do LLMs understand markdown really well? (besides the simple, terse and readable syntax of markdown) They say "LLMs are trained on the web", are the web pages converted from HTML into markdown before being fed into training?

I think it says in the Anthropic docs they use markdown internally (I assume that means were trained on it to a significant extent).

Re: Minifying HTML for GPT-4o: Remove all the HTML tags

#40

Post by andybak »

edublancas wrote: post #6
throwup238 wrote: post #4

I don't think that Mercury Prize table is a representative example because each column has an obviously unique structure that the LLM can key in on: (year) (Single Artist/Album pair) (List of Artist/Album pairs) (image) (citation link) I think a much better test would be something like "List of elements by atomic properties" [1] that has a lot of adjacent numbers in a similar range and overlapping first/last column t…

thanks a lot for the feedback! you're right, this is much better input data. I'll re-run the code with these tables!

Also - is there a chance GPT is relying on it's training data for some questions? i.e. you don't even need to give it the table.

To be sure - shouldn't you be asking questions based on data that is guaranteed not to be in it's training?

Post reply on HN