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?
Don't trust, verify your AI. nostr:nprofile1qyjhwumn8ghj7en9v4j8xtnwdaehgu3wvfskuep0dakku62ltamx2mn5w4ex2ucpxpmhxue69uhkjarrdpuj6em0d3jx2mnjdajz6en4wf3k7mn5dphhq6rpva6hxtnnvdshyctz9e5k6tcqyp7u8zl8y8yfa87nstgj2405t2shal4rez0fzvxgrseq7k60gsrx6zeuh5t is still the only private AI that lets you see and verify the server code for yourself. Thanks, Hodl 🤙
Discussion
ya this is where i am confused as well
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.