Short Message Compression Using LLMs

Re:Short Message Compression Using LLMs by wat10000 on Monday December 30, 2024 @05:44PM (#42554379)

Fire has evocations, which are videos compressed down to something like just a description, then rendered at the receiving end in a way that hopefully has some resemblance to the original.

One viewer stumbles onto a key insight about the struggle taking place, but they only have evocations so they’re not sure. And they sound like a total kook so everyone ignores them.

[ Parent | on HN ]

Re:Short Message Compression Using LLMs by dekhn on Monday December 30, 2024 @06:46PM (#42554893)

I can't find an exact reference and I don't want to spoil too much, I think this was in Children of the Sky, at some point one of the wolf creatures is imprisoned and somebody uses the ship's reduced AI to spy on them.

[ Parent | on HN ]

Re:Short Message Compression Using LLMs by abecedarius on Monday December 30, 2024 @10:07PM (#42556028)

Slight correction: the person with the spy system didn't believe its reports in the end -- the doubt/dismissal problem came before sharing with others, as I remember it. Agreed this was in Children of the Sky.

(aFutD also had a case of high-stakes suspicion of highly compressed messages during Zone turbulence, as I think the GP meant.)

[ Parent | on HN ]

Re:Short Message Compression Using LLMs by askvictor on Monday December 30, 2024 @10:29PM (#42556161)

I shudder to think how current LLMs would go with this. I guess we can currently do this easily for still images and audio. Kind of reminds me of Translation Party.

[ Parent | on HN ]

Re:Short Message Compression Using LLMs by duskwuff on Monday December 30, 2024 @10:35PM (#42556198)

"Hexapodia is the key insight."

[ Parent | on HN ]

Re:Short Message Compression Using LLMs by taylorius on Tuesday December 31, 2024 @06:20AM (#42558042)

I see you Twirlip of the mists

[ Parent | on HN ]