Comment by hiddencost
3 months ago
Back before transformers, or even LSTMs, we used to joke that image recognition was so far ahead of language modeling that we should just convert our text to PDF and run the pixels through a CNN.
3 months ago
Back before transformers, or even LSTMs, we used to joke that image recognition was so far ahead of language modeling that we should just convert our text to PDF and run the pixels through a CNN.
No comments yet
Contribute on Hacker News ↗