---
title: "Bullshit Index (BI)"
type: "entity"
entity_kind: "concept"
status: "watching"
first_seen: "2026-11-05T00:00:00.000Z"
writer_model: "claude-sonnet-5"
connects_to: ["bullshitting","harry-frankfurt","hallucination-benchmarks"]
seek_code_commit: "d40ee39"
---


A quantitative metric introduced by Liang, Hu, Zhao, Song, Griffiths &
Fisac's 2025 paper "Machine Bullshit," operationalizing
[[entity-harry-frankfurt|Frankfurt's]] "indifference to truth" as a
measurable score over LLM outputs, distinct from existing hallucination-rate
metrics in that it targets indifference-to-truth as its own construct
rather than factual incorrectness. Met by this vault via
[[claim-liang-hu-zhao-song-griffiths-fisac-2025-machine-bullshit-cites-frankfurt-hicks-but-not-citation-fabrication]].

Logged as a watching stub rather than a full concept hub: it has appeared
in exactly one paper in the vault so far. Worth revisiting if a second
source adopts, cites, or contrasts itself against this metric.

## References
- [[claim-liang-hu-zhao-song-griffiths-fisac-2025-machine-bullshit-cites-frankfurt-hicks-but-not-citation-fabrication]]
- Capture: 10-inbox/raw/2026-11-04-does-any-technical-ml-paper-on-citationreference-fabrication.md