[alanfranz]

I think it’s an old analogy, and a good one. LLMs are for knowledge what mp3s were for audio.

This was widely discussed in the past years as well.

[cush]

It's a terrible analogy because LLMs are already for audio what LLMs are for audio. You can use LLMs to create new songs and sounds. Encyclopedias don't create new songs.

[simonw]

The older analogy was to JPEG compression - I linked to that in my post (the Ted Chiang link). https://www.newyorker.com/tech/annals-of-technology/chatgpt-...

[saberience]

This analogy has been used for machine learning since way before ChatGPT, my co workers and I were discussing this idea but for LSTM models in roughly 2018.

What’s old is new again.