Muse Spark 1.2 continues Meta's AA-Omniscience pattern: the score rose from 18 to 22, driven by abstention for the second consecutive release. The hallucination rate fell 10 points (38% to 28%) as the attempt rate dropped to 67%, while accuracy slipped from 41% to 38%. Heavy abstention drives both the low hallucination rate and the lower accuracy
hallucination — When a model states something false with full confidence — inventing facts, citations, or APIs that don't exist.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Why it matters
Knowing that a model's honesty score improved by answering less often rather than knowing more changes how you'd deploy it in retrieval or AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → loops where abstention costs you a step.
