Zero data retention is why enterprises self-host: Azure ZDR requires approval, no ZDR for fable
HanchungLee · x · 2026-11-10
Responding to Gergely Orosz on why companies build their own inference stacks, Hanchung Lee adds key details: running OpenAI and Anthropic models through hyperscalers with Zero Data Retention (ZDR) counts as first-party access, keeping sensitive data out of third-party hands.
- Azure is trickier: no ZDR by default; customers must be approved to be removed from safety monitoring
- fable has no ZDR option at all
This explains why companies with highly sensitive data often prefer self-hosting over third-party API providers.
More from Infra
- FlashState inference system doubles vLLM throughput on GLM 5.3 Flash, cuts latency 3.7x — zainhas · 2026-11-10
- UC Berkeley open-sources FreeToken, an edge-native engine running frontier MoE models on consumer hardware — petrusenko_max · 2026-11-10
- NVIDIA's CPU-ARC: reasoning caches 16–291x cheaper with frontier-level performance — nvidia · 2026-11-10
- One slide: when to use Agent Sandbox vs Agent Substrate for agent infrastructure — davemccollough · 2026-11-10
- Godzilla and Sonic on silicon: the chip industry's lost die-art easter eggs — thehiphopswami · 2026-11-10
- MLCommons lays out SC26 MLPerf agenda with Training v6.1 results and roadmap session — TheKanter · 2026-11-10