R0055/2026-04-01/C020 — Assessment

Research	R0055 — RLHF Yes-Men Claims
Run	2026-04-01
Claim	C020

BLUF

Largely correct but with emerging exceptions. No major AI vendor (OpenAI, Anthropic, Google, Meta) offers dedicated anti-sycophancy API parameters or enterprise-configurable sycophancy tiers. OpenAI's model spec mentions avoiding sycophancy as a design principle. A community project (SYCOPHANCY.md) exists but is not a vendor product. Georgetown Law notes companies have tools but have not deployed them.

Probability

Rating: Likely (55-80%)

Confidence in assessment: Medium

Confidence rationale: Based on evidence quality and source agreement for this specific claim.

Reasoning Chain

1. OpenAI's model spec says the assistant shouldn't 'just say yes to everything (like a sycophant).' But this is a design principle, not a configurable API parameter. Georgetown Law notes companies 'have... [SRC01-E01, High reliability, High relevance]

2. JUDGMENT: Largely correct but with emerging exceptions. No major AI vendor (OpenAI, Anthropic, Google, Meta) offers dedicated anti-sycophancy API parameters or

Evidence Base Summary

Source	Description	Reliability	Relevance	Key Finding
SRC01	OpenAI Model Spec / Georgetown analysis	High	High	No vendor offers dedicated anti-sycophancy API parameters; OpenAI model spec addresses it as design principle

Collection Synthesis

Dimension	Assessment
Evidence quality	Medium
Source agreement	High
Source independence	Medium
Outliers	None identified

Detail

Largely correct but with emerging exceptions. No major AI vendor (OpenAI, Anthropic, Google, Meta) offers dedicated anti-sycophancy API parameters or enterprise-configurable sycophancy tiers. OpenAI's model spec mentions avoiding sycophancy as a design principle. A community project (SYCOPHANCY.md) exists but is not a vendor product. Georgetown Law notes companies have tools but have not deployed them.

Gaps

Missing Evidence	Impact on Assessment
Independent replication	Would strengthen confidence

Researcher Bias Check

Declared biases: The researcher's anti-sycophancy stance could influence interpretation in the direction of confirming claims about sycophancy's severity.

Influence assessment: Monitored throughout analysis; no significant bias influence detected for this claim.

Cross-References

Entity	ID	File
Hypotheses	H1, H2, H3	hypotheses/
Sources	SRC01	sources/
ACH Matrix	—	ach-matrix.md
Self-Audit	—	self-audit.md