Y
Hacker News
new
|
ask
|
show
|
jobs
by
dawg91
122 days ago
They do verifiable inference on TEEs for the open source models. The anthropic ones I think they basically proxy for you (also via trusted TEE) so that it cant be tied to you. VPN for LLM inference so to speak.
1 comments
ramoz
122 days ago
Can you link to the verifiable inference method?
link
dawg91
122 days ago
https://docs.near.ai/cloud/verification/
link