←back to thread

Andrej Karpathy: Software in the era of AI [video]

(www.youtube.com)
1480 points sandslash | 4 comments | 19 Jun 25 00:33 UTC | HN request time: 0.633s | source
Show context
nodesocket ◴[19 Jun 25 03:00 UTC] No.44315062[source]▶
llms.txt makes a lot of sense, especially for LLMs to interact with http APIs autonomously.

Seems like you could set a LLM loose and like the Google Bot have it start converting all html pages into llms.txt. Man, the future is crazy.

replies(3): >>44315157 #>>44315298 #>>44315385 #
1. practal ◴[19 Jun 25 04:16 UTC] No.44315385[source]▶
If you have different representations of the same thing (llms.txt / HTML), how do you know it is actually equivalent to each other? I am wondering if there are scenarios where webpage publishers would be interested in gaming this.
replies(2): >>44315617 #>>44315789 #
2. andrethegiant ◴[19 Jun 25 05:09 UTC] No.44315617[source]▶
<link rel="alternate" /> is a standards-friendly way to semantically represent the same content in a different format
replies(1): >>44326650 #
3. jph00 ◴[19 Jun 25 05:40 UTC] No.44315789[source]▶
That's not what llms.txt is. You can just use a regular markdown URL or similar for that.

llms.txt is a description for an LLM of how to find the information on your site needed for an LLM to use your product or service effectively.

4. diggan ◴[20 Jun 25 11:15 UTC] No.44326650[source]▶
Also HTTP headers Accept/Content-Type which in theory could let you serve HTML, XML and JSON all under the same URL/URI but depending on Accept values.