HN Explorer

Ask HN: (Why) Was the LLM breakthrough useful for images, audio, etc.?

1 points by rogerrogerr ↗ HN
This has been bothering me for a while. I feel like I have a decent conceptual grasp of what LLMs are doing with written text. But it seems like they also unlocked a bunch of progress in understanding and generating images, audio, and video. I can’t twist my brain into understanding the connection.

Is the boom in generated non-text content also built on LLMs, or is it just correlated with it because a bunch of excitement drove investment into the industry? I’m hoping for an ELI-non-ai-but-cs-major, this has been bothering me for a while.

6 comments

[ 28.5 ms ] story [ 113 ms ] thread
verdverm
transformers were first an image understanding technique, the text processing came later, it's all about the training data and gradient descent, and allegedly attention
laruss5
It's actually the other way round - the Transformer architecture was introduced for text (machine translation) in "Attention Is All You Need" (2017). Vision Transformers, which apply it to images, came three years later in 2020: https://arxiv.org/abs/2010.11929
verdverm
right, it was not text generation per-se (completion/contemporary understanding) that came first, vision was before that, translation before that
kypro
While some neural network architectures can be designed to better fit certain tasks they are at their core general-purpose learning algorithms which can approximate any target function.

> I feel like I have a decent conceptual grasp of what LLMs are doing with written text

Just think of it as input data. In theory it shouldn't matter what each token represents. They could be xbox controller buttons, image pixels, or text.

The model with enough training data will map those inputs to an expected output.