News for hackers. Stuff that matters.

A comment on Language Models Are Injective and Hence Invertible.

Re:Language Models Are Injective and Hence Invertible by kobelb on Thursday October 30, 2025 @06:19AM (#45758293)
Are the weights invertible, or are the prompts being fed into the model invertible?
[ Parent | on HN ]
Re:Language Models Are Injective and Hence Invertible by singularity2001 on Thursday October 30, 2025 @06:54AM (#45758542)
The prompt is reconstructable from the (latent) representation vector but obviously not from the output
[ Parent | on HN ]