Viewing profile — FrasiertheLion

[dead]

That's basically what we built at Tinfoil. We run open source models inside secure enclaves (also using Intel TDX/AMD SEV-SNP + NVIDIA Confidential Computing). All the code running…

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 op…

Overall I'm bullish on standardized local APIs that ship with the browser or platform. Far more tractable than expecting end users to stand up their own local model instances, thou…

Very reasonable if you have the resources to run it locally and certainly the best option. But we created Tinfoil because not everyone has that capability especially when it comes …

Unfortunately we don’t support crypto payments at this time as we use Stripe. We try to add models selectively as we have to be mindful about our compute allocation. Is there a spe…

Yes we do, but the load balancer also runs inside the enclave and is attested: https://github.com/tinfoilsh/confidential-model-router In turn, that attests the model enclaves, for …

Yeah everything is open source if you’re good at reversing. Models are increasingly capable of converting binaries into source, and excellent at implementing systems when there’s a…

This was largely true before. But AI reduces the cost of comprehension and finding vulnerabilities en-masse to zero, so this no longer holds, and I’m increasingly convinced that hi…

Oh that's quite interesting and hasn't been my experience with regular backend code specifically with respect to tool calling. However that could be because the tool calling format…

Because V4 doesn't even beat Kimi K2.6 and GLM 5.1, which have been out longer. It's only talked about as much as it is because it's Deepseek and R1 was the first open source reaso…

You can use Tinfoil for inference, which lets you use the model in the cloud while getting similar privacy as running locally: https://tinfoil.sh/inference . Disclaimer I'm the cof…

Have you given GLM 5.1 or Kimi K2.6 a shot for coding? They outperform Deepseek v4 pro.

This is the canonical use case for Tinfoil: https://tinfoil.sh/inference . It provides verifiably private AI inference with frontier open source models: https://docs.tinfoil.sh/mod…

It's 80 minutes, not 80 hours.

Yes they absolutely care and have been doing serious work to migrate PKI to PQC. This was the first of several articles coming out of Google: https://blog.google/innovation-and-ai/…

It's unfortunate that we're past the point where all quantum computing progress is public. Between this and the unbearable secrecy of AI labs, balkanization of knowledge is in full…

Tanya from the Tinfoil team that worked on the confidential computing and security substrate here. Also around to answer any questions!

We don't have reproducible builds because we attest the full OS image that we run, which is the Ubuntu image. Unfortunately bit-by-bit reproducible binaries for OS images is kind o…

Enclaves have a property that allows the hardware to compute a measurement (a cryptographic hash) of everything running inside it, such as the firmware, system software such as the…

The model is running in a secure enclave that spans the GPU using NVIDIA Confidential Computing: https://www.nvidia.com/en-us/data-center/solutions/confident... . The connection is…

Arguably this is less useful for consumer hardware in the first place. This is mostly useful when I don’t trust the service provider with my data but still need to use their servic…

Most people outside of a narrow set of cryptography engineers are unfamiliar with the term anonymous credentials, while age and identity verification are two privacy-invasive requi…