Lebrel open beta: encrypted uncensored inference with signed receipts registered on Solana
HeyAmit_ · x · 2026-11-05
Lebrel launches an open beta for encrypted, verifiable uncensored editions of frontier open-weight models: requests are encrypted from your device into attested hardware, every answer carries a signed receipt naming the exact model, precision and engine, with fingerprints registered on Solana and verifiable in-browser. It claims no added refusal layer, no stored prompts, and detection of silent model swaps — motivated by Anthropic's September 2026 report of labs passing off Claude answers as their own. Free 4-hour daily windows on the uncensored edition.
More from Models
- 500K GPU-hours MoE Handbook: 18 of Top 20 Open-Weights Models Are MoEs — Nouamanetazi · 2026-11-06
- RicursiveAI Releases From-Scratch Dense Ripple-65B, Tops 80% on Terminal Bench 2.1 — DZhang50 · 2026-11-06
- NVIDIA touts time-to-market and quality benefits of its seven open AI models — karlfreund · 2026-11-06
- Ripple-65B on one RTX PRO 6000: 110-120 tok/s on code in local agent tests — DZhang50 · 2026-11-06
- Devs revisit dense models: should we build more above 27B? — DZhang50 · 2026-11-06
- DeepSeek-V4.1-Flash runs on one RTX 3090 at 41 tok/s with Delta Inference Engine v0.93 — musicurgy · 2026-11-06