On Fri, Apr 18, 2025 at 01:35:19PM +0800, jeremy ardley wrote: > > On 18/4/25 13:10, to...@tuxteam.de wrote: > > > I'm not sure if it is mentioned but just take a picture of each page and > > > ask > > > a good Large Language Model to give you a table. > > After this, I'd double-check each individual number. You'll never know > > if they are being made up, otherwise. > > > I've been doing this for a couple of years now scanning bank statements etc.
[...] I'm not going to argue with a believer. Do as you see fit. Usually, the reasoning is that humans do errors. But we humans have had quite a long while to learn to debug human made errors. Those made by LLMs look significantly different to me: I'm pretty sure this is going to be an issue. I see my colleagues now writing programs with LLMs. I don't look forward to the day I'll have to debug a larger corpus of this mess. Cheers -- t
signature.asc
Description: PGP signature
