Cloudflare discloses cross-request KV cache exposure in GLM-5.3 on Workers AI (155 responses)
wondersky · hn · 2026-10-27
Cloudflare published a postmortem on a cross-request KV cache exposure bug affecting the GLM-5.3 model served via Workers AI, where cached state could leak across users' requests, impacting 155 responses. The post covers root cause, scope, and remediation — a notable case study in shared-cache inference security.
More from Infra
- AI Cloud Operators Sell Years of Compute Yet Struggle to Finance Delivery — AccBalanced · 2026-10-27
- Modal engineer's deep dive into how vLLM and SGLang inference engines work — charles_irl · 2026-10-27
- TSMC reportedly preparing another CoWoS price hike of up to 20% as AI packaging demand outstrips supply — rohanpaul_ai · 2026-10-27
- Anthropic S1 could be the neocloud bottom: GPU prices hit all-time highs, argues Nic Carter — inductionheads · 2026-10-27
- Ollama v0.40.11 adds on-device speech synthesis on macOS and ships d3 decision models — emmanuelvivier · 2026-10-27
- SpaceX secures $40B debt for AI chip purchases, backed by Starlink revenue — emmanuelvivier · 2026-10-27