Reverse-engineering Apple's on-device personal knowledge graph: 181 entity classes, 278 predicates
JeremyCMorgan · x · 2026-11-11
Eighth Rank reverse-engineered Apple's on-device Personal Knowledge Graph shipped with macOS 13: a pair of daemons build a local graph of who you know and what you do, cross-referencing Contacts, Calendar, Photos, Messages, Mail, location and Screen Time. The graph carries 181 entity classes and 278 predicates with confidence and provenance, queryable by LLMs with almost no official documentation. A production case study for agent memory, provenance, and privacy boundary design; the authors also shipped a tool to inspect your own graph.
More from Safety
- Microsoft Research: editing under 10 neurons turns an agent into a sleeper backdoor — DimitrisPapail · 2026-11-11
- Safety community's best spend: a 2-year institution teaching LLM internals — viemccoy · 2026-11-11
- The same people cite an existential AI race with China and want looser GPU export controls — austinc3301 · 2026-11-11
- Redwood reframed: doing narrow safety work to buy odds, not solve AI safety broadly — austinc3301 · 2026-11-11
- Polymarket puts 11% odds on a US AI safety bill passing this year — Polymarket · 2026-11-11
- OpenAI board member tells audience AI accident is 'the most likely reason you will die' — Polymarket · 2026-11-11