Post

so you’re saying you need software that is natively multimodal, good at conversions, can work in iterative verification loops, and is good at navigating complicated proprietary formats with intuitive prodding? Hmm

seed paste soy goblin@phasebinary.bsky.social

"we don't need fire, we just need a way to cook our food"

27/10/26, 11:31 am6 reposts126 likes

Kimmy W

@ghostynewt.bsky.social

you’re right but “good in conversations” is a huge antifeature in a PDF converter

aly

@aly.codes

I highly suggest reading my post back to yourself out loud

Kimmy W

@ghostynewt.bsky.social

pdf conversion should be a oneshot command like docling or allenAI’s olmOCR, I don’t want to go back and forth with an agent on a task like that i agree with your other points though, sorry for being annoying & not getting it

1G-N15 ⬡

@1gn15.com

I think what aly's trying to say is that such a command line tool most likely uses AI in the backend to convert it back into docx. AI usage doesn't have to be chatbot-style.

Vika 🏳️‍⚧️

@vikanezrimaya.xyz

they don't want an iterative verification loop, they want it to one-shot everything in a second, like a magic button

max power 🌌

@sneptech.bsky.social

almost invariably when something like this is said, it's by someone who thinks AI is chatgpt dot com rather than an AI agent in a harness working within one's computer

max power 🌌

@sneptech.bsky.social

like the chasm in capability experience there is so fucking huge it boggles the mind