alt Hacker NewsI think we should separate the private AI discussion from the local AI discussion. The pragmatic choice to run big LLMs is one/several big servers online, but that doesn't mean private companies should be the only ones to run them.
A self hosted inference solution that offer good tenant isolation guarantees (ideally zero trust) and is easy enough to deploy and maintain (think Plex for AI) would be my choice for privacy. Now to be honest I have done zero research about this and have zero idea how feasible that is, maybe it already exists and there's some discord servers I should join?
Edit: I don't need to mention it here but what's incredible is that open models are in the ballpark of the best commercial models so supposedly, the hardest part by far is already solved.
Another option is verifiably private inference with open source models running inside secure enclaves on the cloud (using NVIDIA confidential computing), and the enclave code is open source and verified via remote attestation upon connection, cryptographically proving that the inference provider cannot see any data. Tinfoil: https://tinfoil.sh/ is a good example of this (disclaimer: i'm the cofounder). You can read more about how this works here: https://docs.tinfoil.sh/verification/verification-in-tinfoil
>that open models are in the ballpark of the best commercial models
This is basically true for certain tasks. As an example, chat interfaces are not well poised to take advantage of higher model intelligence than what the best open source models already provide. But coding harnesses still benefit from greater model intelligence and even more so, the reinforcement learning that tightly interlinks the provider's coding harness (claude-code, codex) with the model's tool calling interfaces is another reason for discrepancy in effectiveness even when controlled for model intelligence. The opencode founder (open source coding harness that supports different model providers) was recently complaining about the challenges making the harness work well with different providers: https://x.com/thdxr/status/2053290393727324313