High impact
Cross-request KV cache exposure in the GLM-5.3 Workers AI model (155 responses)
What happened
A configuration mismatch in the GLM‑5.3 model on Workers AI caused an SGLang bug that leaked KV cache pages between requests, affecting 155 responses to very long prompts between August 27 and September 9, 2026. Cloudflare fixed the misconfiguration, patched the inference engine, and restored the model on September 9.
Why it matters
The incident shows that misconfigured inference engines can breach tenant isolation, potentially exposing other users' data in long‑context AI calls.
Is this a big deal?
Get stories like this every morning
The day's AI news in plain English, in your inbox at 8:30 IST. Free.
More AI news
Show HN: New Cartesia Text-to-Speech ModelIndustry news · 13 Nov 2026Chicago schools to Google – we'd rather lose Search than be forced to accept AIIndustry news · 13 Nov 2026Introducing ChatGPT WalletOpenAI · 13 Nov 2026Shield helps technicians hand off legacy portal work with OpenAIOpenAI · 13 Nov 2026How AI Is Helping Care Teams Get Patients the Right Care, SoonerNVIDIA · 13 Nov 2026This page was collected from blog.cloudflare.com and summarised automatically by AIPulsee's pipeline. See how it runs.