Fetching from the wire…
01
02
03
04
05
06
07
08
Security2026-05-25 · source-backed
New research shows unrestricted cross-user KV cache sharing in LLM serving creates side-channel attacks where adversaries infer other users' inputs by probing for cache reuse. CachePrune introduces privacy-aware sharing that prevents leakage while preserving 85%+ cache reuse. If you're running multi-tenant inference, this paper is required reading.
Each link below shares sources, entities, or timing with this story.
Simon Willison released LLM / Shared entity: LLM / Shared topic / What happened next
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; overlapping topics (input, serving).
Simon Willison released LLM / Shared entity: LLM / What happened next / Tension
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; picks up the LLM thread on 2026-08-16.
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; picks up the LLM thread on 2026-07-27.
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; picks up the LLM thread on 2026-06-19.
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; picks up the LLM thread on 2026-06-18.
Simon Willison released LLM / Shared entity: LLM / What happened next
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; picks up the LLM thread on 2026-08-21.
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; picks up the LLM thread on 2026-08-17.
Simon Willison released LLM / Shared entity: Multi / What happened next
Linked by a graph relationship (Simon Willison released LLM); both cover Multi; picks up the Multi thread on 2026-08-17.