C018¶


Research	R0057 — RLHF Yes-Men Claims v3
Run	2026-04-01
Claim	C018

Claim: Anthropic and OpenAI are working on sycophancy reduction at the model level — general improvements that ship to everyone.

BLUF: Confirmed. Anthropic reports 70-85% sycophancy reductions in Claude 4.5 models compared to Opus 4.1, using the Petri evaluation set. OpenAI reports substantial sycophancy improvements in GPT-5 and released public evaluations. Both ship improvements to all users.

Probability: Very likely (80-95%) | Confidence: High

Summary¶

Entity	Description
Claim Definition	Claim text, scope, status
Assessment	Full analytical product with reasoning chain
ACH Matrix	Evidence x hypotheses diagnosticity analysis
Self-Audit	ROBIS-adapted 5-domain audit

Hypotheses¶

ID	Hypothesis	Status
H1	Both are working on model-level sycophancy reduction	Supported
H2	Both are working on it but progress varies	Not supported
H3	Neither is working on sycophancy reduction	Eliminated

Searches¶

ID	Target	Results	Selected
S01	Anthropic OpenAI sycophancy reduction model level general improvements	10	1

Sources¶

Source	Description	Reliability	Relevance
SRC01	Anthropic and OpenAI sycophancy reduction announcements	High	High

Revisit Triggers¶

If either company reverses course on sycophancy reduction efforts