Safety · Concept
Scene-Level Audit of LLM-Generated Autobiography Confabulation
Case study finds 96.7% of LLM memoir days fail verification, dominated by grounded drift of real entities into invented scenes.
Forecast horizon
Connections
Connections · 2
How this node ties into the rest of the map, and the evidence behind each link.
to · tracked by 3/10
arXiv cs.AI Feed (2026-08-26) Scene-level autobiography confabulation audit is published in the cs.AI feed.
+3 growth to · informs 3/10
LLM Lie Detection and Deception Auditing Scene-level memoir audit quantifies grounded confabulation as a dominant failure mode for life-writing LLMs.
+3 growthSignal sources
Signal sources
Dated facts from primary sources in this direction.
US evaluation centre Jun 2025
In June 2025 the US AI Safety Institute was renamed the Center for AI Standards and Innovation (CAISI), pivoting toward security, standards and adversary-model assessment.
NIST → Frontier safeguards May 2025
Anthropic activated its ASL-3 deployment and security standard with Claude Opus 4 on 22 May 2025 — the first real-world trigger of a responsible-scaling tier, focused on blocking bio-weapon uplift.
Anthropic → Cross-border testing 2025
The International Network of AI Safety Institutes (launched Nov 2024) ran a third joint testing exercise focused on agentic AI systems across cyber and fraud strands.
European Commission — AI Office →