Fetching from the wire…
01
02
03
04
05
06
07
08
Research2026-08-14 · source-backed
arXiv 2608.13050 fed the same CTI report, same instructions and same LLM to Microsoft GraphRAG versus vector-similarity RAG, then rotated every IP, domain and file hash. In an APT28 case study the GraphRAG plan kept 100% of its detections firing, the naive plan kept 29%. Replicates across nine real CTI reports from four vendors. The authors note prompt wording matters nearly as much as the retrieval backend, which is an honest caveat most papers skip.
Each link below shares sources, entities, or timing with this story.
LLM uses OpenAI / Shared entities / Earlier coverage / Tension
Linked by a graph relationship (LLM uses OpenAI); both cover LLM, RAG; earlier LLM coverage from 2026-07-27.
LLM uses OpenAI / Shared entity: LLM / Same source domain / Earlier coverage / Tension
Linked by a graph relationship (LLM uses OpenAI); both cover LLM; reported by the same outlet (arxiv.org).
Simon Willison released LLM / Shared entity: RAG / Same source domain / Earlier coverage
Linked by a graph relationship (Simon Willison released LLM); both cover RAG; reported by the same outlet (arxiv.org).
Simon Willison released LLM / Shared entity: LLM / Earlier coverage / Tension
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; earlier LLM coverage from 2026-06-19.
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; earlier LLM coverage from 2026-06-18.
LLM uses OpenAI / Shared entity: LLM / Earlier coverage
Linked by a graph relationship (LLM uses OpenAI); both cover LLM; earlier LLM coverage from 2026-07-31.
Linked by a graph relationship (LLM uses OpenAI); both cover LLM; earlier LLM coverage from 2026-06-19.
LLM uses OpenAI / Shared entity: RAG / Earlier coverage
Linked by a graph relationship (LLM uses OpenAI); both cover RAG; earlier RAG coverage from 2026-04-24.