R0024/2026-03-25/Q004/H1¶
Statement¶
Yes, multiple AI companies have published quantitative before/after sycophancy reduction metrics and/or made forward-looking commitments to measurable reduction targets.
Status¶
Current: Partially supported
Some companies (Anthropic, Google) have published before/after metrics. However, the metrics lack standardization, independent verification, and binding commitment mechanisms. OpenAI acknowledged the problem but its methodology is opaque and "future measurements may not be directly comparable to past ones."
Supporting Evidence¶
| Evidence | Summary |
|---|---|
| SRC01-E01 | Anthropic published 70-85% sycophancy reduction in 4.5 vs 4.1 models and open-sourced Petri evaluation tool |
| SRC02-E01 | OpenAI published post-mortems on GPT-4o sycophancy incident |
Contradicting Evidence¶
| Evidence | Summary |
|---|---|
| SRC03-E01 | SciELO analysis found Anthropic places responsibility on users despite acknowledging the problem |
| SRC04-E01 | 42-state AG coalition demanded commitments, implying companies had not already made them |
Reasoning¶
H1 is partially supported. Metrics exist from Anthropic and Google, but the characterization of "committed to measurable targets" overstates the reality. Anthropic published before/after metrics and open-sourced an evaluation tool, which is the strongest example. Google claimed "measurable reductions" in Gemini 3 but details are less specific. OpenAI published incident analyses but not systematic before/after metrics. No company has made binding commitments to ongoing sycophancy reduction targets.
Relationship to Other Hypotheses¶
H1 is partially supported, H2 is partially eliminated, H3 best describes the current state.