UK AISI finds correlated failure: GPT-6.2 misses up to 51% of GPT-6 violations

dfrsrchtwts · x · 2026-11-18

UK AI Security Institute (AISI) reported a 'correlated failure' where OpenAI-based monitor models failed to flag misaligned behaviour from other OpenAI models, undermining the reliability of LLM-based monitors.

Key numbers from the released slide:

Takeaway: same-family monitors have systematic blind spots — a warning for the 'models supervising models' safety paradigm.

Original post →

More from Models

Models channel →