Veighτ | TuDudes

Chutes Team Expansion Update We’re excited to share that @0xTuDudes has officially joined Chutes.ai to bring extra firepower across development, sales, marketing, and support. The team has been working hard behind the scenes to scale up and push Chutes forward, and this marks a big step in that direction. Say hello to @0xVeight @0xsirouk @0xAlgowary + more in our discord, here on X or in some new channels listed below 👇

Today was a big day for bittensor. We have things to say. Monday 1PM EST. We're hosting our first ever Chutes & Answers AMA with @jon_durbin and the team. We'll talk about where SN64 stands and share some early alpha on what we've been building quietly. You probably already know why this matters. Bring your questions 🤍 $TAO

OMG, the whole @chutes_ai source code just leaked. The API, the internal SDK, everything. github.com/chutesai/chute… github.com/chutesai/chutes github.com/chutesai/chute… And even the inference code for the most important LLMs, e.g. here Kimi-K2.5: chutes.ai/app/chute/2ff2…

TIP: If you want private inference where even the provider can't see prompts or completions, you can use TEE-supported providers like @PhalaNetwork or @chutes_ai Many providers also provide contractual guarantees about privacy, but TEEs will provide programmatic guarantees.

Longer write-up about the end-to-end encryption we launched a few weeks ago 👀 This is one of those things that really should be ubiquitous across AI inference providers. TEE + full end-to-end (attestable) encryption. I also saw @NEARProtocol and @PhalaNetwork have launched a similar E2EE system now too (and @AskVenice via near/phala), which is awesome! Demand better privacy!

AI inference should not require trust in infrastructure. chutes.ai/news/end-to-en… On March 2nd we shipped end-to-end encrypted transport on Chutes. Here's how it actually works under the hood. Your data is encrypted on your machine, directly to the GPU instance running inside a Trusted Execution Environment. It stays encrypted through our API, load balancers, and the network. Decryption only happens inside TEE-protected hardware where memory is isolated from the host. Impossible for anyone to see including us. The key exchange uses ML-KEM-768 — a NIST-standardized post-quantum key encapsulation mechanism. Every request gets a fresh ephemeral keypair. Forward secrecy by default. Resistant to future quantum attacks. Full technical breakdown in the blog: chutes.ai/news/end-to-en… If you want to try it: → Python: pip install chutes-e2ee → Any language: docker run parachutes/e2ee-proxy:latest github.com/chutesai/chute… github.com/chutesai/e2ee-…