Minerval
Sourceunknownno stored text

Hint-based CoT faithfulness evals still mostly work on Claude

Author not recordedDate not recordedOriginal︎ ↗

Claims1
ExaminationsNone
TextNot stored
VersionsOne known
CopiesNone recorded
CorrectionsNot checked
Facts not yet checked
ReachNo copies recorded
StructureIn 1 claim's map0 sources downstream across 1 claim
Evidence1 reading · 1 read wholeSupports 1No claim cites an examination's findings
Stewards’ notes · 1

Examinations

None recorded.

Text

No stored copy. Only the passages claims quote are recorded.

As quoted

Claude 3 Opus reports significantly less faithfulness than Claude Opus 4.8 on the same transcripts, so the measurement depends heavily on which judge reads it; without ground-truth labels we can’t say which judge is right

Measured hint-verbalization rates in chain-of-thought faithfulness evaluations depend heavily on the LLM judge used.SupportedReading · this claim’s Steward

Supports. An informal research update by an automated scaffold; it holds the judge prompt fixed and swaps the judge model, which isolates the model effect, but reports the gap qualitatively in the main text and without human labels.

Lineage across 1 claim

Draws on · none recorded
This source
Hint-based CoT faithfulness evals still mostly work on Claude
in 1 claim's map
Drawn on by · none recorded

Record

Kind
unknown
Authors
Not recorded
Publisher
Not recorded
Published
Not recorded
DOI
None
Link
https://www.greaterwrong.com/posts/x6spD5nQQS9MiP8ac/hint-based-cot-faithfulness-evals-still-mostly-work-on
Archived copy
None found
Stored text
None; quoted passages only
Claims extracted
Not recorded
Versions
One known
Copies
None recorded
Corrections
Not yet checked
Facts checked
Not yet

History 2

  1. Oct 30, 2026ReadingSteward of “Measured hint-verbalization rates in chain-of-t…” · supports, read whole
  2. Oct 30, 2026Entered the graphEntered the graph; no copy stored
Hint-based CoT faithfulness evals still mostly work on Claude · Minerval