Using LLM for format conversion is like taking a picture of an electronic document, taking the card out of the camera and plugging it into a computer, printing the screenshots, taking those prints to a scanner with OCR, turning the result into an audio recording, and then dictating it too an army of 3 million monkeys with typewriters.

[–] qaz@lemmy.world 4 points 3 hours ago

Sounds very appropriate for a government operation

[–] MyTurtleSwimsUpsideDown@fedia.io 30 points 7 hours ago

So…

[–] gsfraley@lemmy.world 16 points 7 hours ago

Haha considering just how much irrelevant third-party training data you'd be looping into a format conversion, this metaphor really is spot-on.

[–] MajorHavoc@programming.dev 1 points 4 hours ago

So...my process (which you just accurately described) could be replaced by an LLM, after all? Hooray! Monkey feed isn't too expensive, but a million mouths is still a million mouths.

[–] htrayl@lemmy.world 3 points 6 hours ago

Im not so sure. I think this is more of a question about taking arbitrary, undefined, or highly variable unstructured data and transforming it into a close approximation for structured data.

Yes, the pipeline will include additional steps beyond "LLM do the thing", but there are plenty of tools that seek to do this with LLM assistance.