Javascript is not enabled. This site can still works but it'll be more interactive when javascript is enabled.
loading...
Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
with
20 hours ago
|
on: Progress on provable inference for large language models
isn't model substitution a vendor accountability thing? and token tampering, is that not infra security?
do either of these need 70-95x the GPU time in "zksnark" proofs?
reply