Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Donut: OCR-Free Document Understanding Transformer. Parent comment
This seems like exactly the kind of problem that will see rapid improvements as people point more LLMs at multimodal input.
Right now making predictions for ML capabilities on a five year timeframe seems foolhardy.
There are no comments on this comment yet.
This seems like exactly the kind of problem that will see rapid improvements as people point more LLMs at multimodal input.
Right now making predictions for ML capabilities on a five year timeframe seems foolhardy.