On a similar note, I saw a story a bit back of someone saving input tokens by feeding the bot an image of a wall of text rather than the text itself and having it read the image via OCR.

Satire and reality are too hard too distinguish these days.

[–] skisnow@lemmy.ca 8 points 2 days ago

I see this one all the time on LinkedIn, the management rubes love it

[–] SorryQuick@lemmy.ca 3 points 2 days ago (2 children)

Saves input tokens and uses more output because of OCR, and output is priced way higher.

[–] Rooster326@programming.dev 3 points 1 day ago

It's an accounting trick. It uses a different budget....

[–] boonhet@sopuli.xyz 1 points 2 days ago* (last edited 2 days ago)

Also if you're doing anything multi-prompt, that output is re-used as (luckily cached) input tokens for the next prompt anyway lol

[–] topperharlie@lemmy.world 3 points 2 days ago (1 children)

I mean, back in my days (👴) people sent a photo pasted into a word document, so things haven't change that much...

[–] Natanael@infosec.pub 2 points 2 days ago

They still do

[–] brian@programming.dev 1 points 1 day ago

this is the default compaction method in omp now. afaik it's exploiting the pricing structure of the big providers more than anything