Nostr Web Client

I'm trying to understand how maple ai works.

Where is the LLM model running?

I understand that the maple team don't have access to the unencrypted text, but the ones actually running the LLM must access to the unencrypted text, no?

MoMeezy ϟ 𓅦 ₿ 5mo ago

ya this is where i am confused as well

Reply to this note

Please Login to reply.

Discussion

Marks 5mo ago

The LLMs are open source models running in secure enclaves on the GPU. They follow the same attestation process so users can verify privacy. None of the data is ever shared with the creators of the models because they are run in an isolated environment.

MoMeezy ϟ 𓅦 ₿ 5mo ago

are open source models released with weights already populated (trained) or do you train them yourself?

Marks 5mo ago

We use the weights populated. We’ve discussed training models in the future but are not there yet