Unfortunately, verifiable privacy is not physically possible on MacBooks of today. Don't let a nice presentation fool you.

Apple Silicon has a Secure Enclave, but not a public SGX/TDX/SEV-style enclave for arbitrary code, so these claims are about OS hardening, not verifiable confidential execution.

It would be nice if it were possible. There's a lot of cool innovations possible beyond privacy.

▲

znnajdla 2 hours ago | parent | next [-]

As if you get privacy with the inference providers available today? I have more trust in a randomly selected machine on a decentralized network not being compromised than in a centralized provider like OpenAI pinky promising not to read your chats.

▲

ramoz 2 hours ago | parent [-]

Inference providers don't claim private inference. However, they must uphold certain security and legal compliances.

You have no guarantees over any random connected laptop connected across the world.

	▲	rz2k 13 minutes ago \| parent [-]
		Kagi Assistant has a five point scale of estimated privacy levels of models hosted on different providers. https://help.kagi.com/kagi/ai/llms-privacy.html

▲

geon 3 hours ago | parent | prev [-]

Every hardware key will be broken if there is enough incentive to do so. Their claims read like pure hubris.

	▲	znnajdla 2 hours ago \| parent [-]
		Who cares about AI privacy? Most people don’t. If you do, run locally.