21–30 of 111 posts
[flagged]
I read this and your reply to the sibling, you seem to have reputation to be sensible - what are you trying to say? If someone re-implements or reverses a service then it doesn't need to be in the same language.
To make a full implementation of a Apple product, the specification for that Apple product must exist in some form.
Earlier quoted context omitted.
I read this and your reply to the sibling, you seem to have reputation to be sensible - what are you trying to say? If someone re-implements or reverses a service then it doesn't need to be in the same language.
This dude stays commenting on things he doesn't actually understand anything about. I have run into him multiple times in threads on what I do (compilers) and he's clueless but insistent.
As for the matter at hand, I assume that such implementation is validated against which specification exactly?
Gladly to be educated in my clueless.
Reading the whitepaper, the inference provider still has the ability to access the prompt and response plaintext. This scheme does seem to guarantee that plaintext cannot be read for all other parties (e.g. the API router), and that the client's identity is hidden and cannot be associated with their request. Perhaps the precise privacy guarantees and allowances should be summarized in the readme. With that in mind, d…
> the inference provider still has the ability to access the prompt and response plaintext Folks may underestimate the difficulty of providing compute that the provider “cannot”* access to reveal even at gunpoint. BYOK does cover most of it, but oh look, you brought me and my code your key, thanks… Apple's approach, and certain other systems such as AWS's Nitro Enclaves, aim at this last step of the problem: - https:…
Earlier quoted context omitted.
This dude stays commenting on things he doesn't actually understand anything about. I have run into him multiple times in threads on what I do (compilers) and he's clueless but insistent.
Thakfully that the Internet is full of analists with such deep understanding of others personality, otherwise we would all be lost. As for the matter at hand, I assume that such implementation is validated against which specification exactly? Gladly to be educated in my clueless.
Earlier quoted context omitted.
Thakfully that the Internet is full of analists with such deep understanding of others personality, otherwise we would all be lost. As for the matter at hand, I assume that such implementation is validated against which specification exactly? Gladly to be educated in my clueless.
I guess English isn't your first language so nbd but I have no idea what you're asking.
Edit : reminds me of federated learning and FlowerLLM (training only AFAIR, not inference), like... yes, nice, I ALWAYS applaud any way to disentangle from proprieaty software and wall gardens... but like what for? What actual usage?
Earlier quoted context omitted.
I guess English isn't your first language so nbd but I have no idea what you're asking.
To be educated on the public specification of Apple's Private Compute Cloud so that I become less clueless, according to you.
That's nice... in theory. Like it could be cool, and useful... but like what would I actually run on it if I'm not a spammer? Edit : reminds me of federated learning and FlowerLLM (training only AFAIR, not inference), like... yes, nice, I ALWAYS applaud any way to disentangle from proprieaty software and wall gardens... but like what for? What actual usage?
Edit on that too : makes me think of OpenAI Whisper as a service via /e/OS and supposedly anonymous proxying (by mixing), namely running STT remotely. That would be an actual potential usage... but IMHO that's low end enough to be run locally. So I'm still looking for an application here.
Earlier quoted context omitted.
> the inference provider still has the ability to access the prompt and response plaintext Folks may underestimate the difficulty of providing compute that the provider “cannot”* access to reveal even at gunpoint. BYOK does cover most of it, but oh look, you brought me and my code your key, thanks… Apple's approach, and certain other systems such as AWS's Nitro Enclaves, aim at this last step of the problem: - https:…
At the end if the day, Nitro Enclaves are still “trust Amazon”, which is a poor guarantee. NVIDIA+AMD offers hardware backed enclave features for their GPUs which is the superior solution here.