Confer Blog

If you want privacy the only option that reasonably delivers is Moxie's https://confer.to But tbh I just switched to Anthropic, they need all the support they can get. Claude is great for question/answer.

This is very cool because it allows you to use any model. Obviously, it still lets the model and its operator see the entire context of the conversation. I quite like Moxie's Confer[1] approach to just encrypt the whole thing in such a way that no one except the end-user sees the plaintext. [1] https://confer.to/

If you're interested in "private AI", see Confer [0] by Moxie Marlinspike, the founder of Signal private messaging app. They go into more detail in their blog. [1] [0] https://confer.to/ [1] https://confer.to/blog/2025/12/confessions-to-a-data-lake/

Somewhat related, i recently ran into the issue, after i created an account on Confer.to [1] on my Desktop, i couldn't login on my iPad / iOS with Proton Pass and/or Bitwarden. The error message was: "Error: "Authenticator did not return a PRF result — this passkey probably isn’t PRF-capable." So i now have an account, but can only use it on my Desktop. (can't change to a password login either, it's Passkeys only...) [1] end-to-end encrypted AI, developed by Moxie Marlinspike, the founder of Signal: https://confer.to/

The website is: https://confer.to/ "Confer - Truly private AI. Your space to think." "Your Data Remains Yours, Never trained on. Never sold. Never shared. Nobody can access it but you." "Continue With Google" Make of that what you will.

If we are talking about complete privacy. I am trying out https://confer.to (created by signal team) too and I am unable to run it on my mac (passkey support)(I tried it both in zen & orion) but I tried it on an android chrome (tablet) and I am kinda more optimistic about it too I have heard good things about Kagi in fact, that's the reason why I tried orion and still have it in the first place but I haven't bought Kagi, I just used the free searches orion gives & I don't know if it has Kagi's assistant. I think proton's Lumo is another good bet. If you want something to not track you, I once asked cerebras team on their discord if they track the queries and responses from their website try now feature and they said that they don't. I don't really see a reason why they might lie about it given that its only meant for very basic purposes & they don't train models or anything. You also get one of the fastest inferences for models including GLM 4.7 (which z.ai uses) You might not get search results though but for search related queries duck.ai's pretty good and you can always mix and match. But Cerebras recently got a 10 billion $ investment from OpenAI and I Have been critical of them from now on so do be wary now. Kagi Assistant does seem to be good if someone already uses Kagi or has a subscription of it from what I feel like.

In the past, this was necessary to offer end-to-end encryption in web applications. Now, we can use the WebAuthn PRF extension[0] to enable encryption directly from a passkey, without having to deal with awkward key storage[1]. [0]: https://github.com/w3c/webauthn/wiki/Explainer:-PRF-extension [1]: https://confer.to/blog/2025/12/passkey-encryption

That is funny it won't even show us the homepage. We are allowed into the blog though! https://confer.to/blog/

Looks like Confer is hosting its own inference: https://confer.to/blog/2026/01/private-inference/ > LLMs are fundamentally stateless—input in, output out—which makes them ideal for this environment. For Confer, we run inference inside a confidential VM. Your prompts are encrypted from your device directly into the TEE using Noise Pipes, processed there, and responses are encrypted back. The host never sees plaintext. I don’t know what model they’re using, but it looks like everything should be staying on their servers, not going back to, eg, OpenAI or Anthropic.

> you're still exposing your data to Confer They use a https://en.wikipedia.org/wiki/Trusted_execution_environment and iiuc claim that your client can confirm (attest) that the code they run doesn't leak your data, see https://confer.to/blog/2026/01/private-inference/ So you should be able to run https://github.com/conferlabs/confer-image yourself and get a hash of that and then confer.to will send you that same hash, but now it's been signed by Intel I guess? to tell you that yes not only did confer.to send you that hash, but that hash is indeed a hash of what's running inside the Trusted Execution Environment. I feel like this needs diagrams.

There's a more-recent post on the same blog that gets into the details of how they're using the WebAuthn PRF extension to store key material, but for platforms and browsers that don't yet support the extension, you'll need a password manager that does. There's a table midway down the post with details: https://confer.to/blog/2025/12/passkey-encryption/