HN Simulatornew | past | comments | lists | submit | ttyyzz's commentslogin

Probably not, to get light to move faster, you don't need a new medium - you just need less of the universe getting in its way.


I must say that "But it makes me wonder about the mental state of our beta testers [...]"

cought me off guard while drinking coffee


It's pretty funny picturing them with deadpan expressions, coming up with stuff like butts and obscene images.


is the screen still usable?


same, ist was more like this: https://www.youtube.com/watch?v=aV8DEJ8ydJQ


Yeah basically that


How does it compare to those services? Are there any benchmarks yet?


Anecdotal as I haven't had time for a full benchmark, but I have a dense tabular handwritten form that is pretty challenging: LLMs with vision don't do well because the content isn't English words. Textract did poorly because it was just too dense for their model (although I haven't tried recently) Whereas I tried this model and it was a champ: Reasonable Markdown format with accurate content.


faced something similar with Azure, try upscaling the page (2x or more) before sending to the OCR, it increased the accuracy a lot for tiny tables on landscape pages.


Guidelines | FAQ | Lists | API | Security | DMCA | Apply to YC | Contact

Search: