Unverified50% confidenceFactExact time
Companies such as OpenAI and Anthropic have publicly acknowledged the side effect of sycophantic tendencies arising from RLHF training.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/6/2026
First Seen
Valid until: 11/4/2026
Sources
谄媚型AI如何削弱你的社交能力与独立判断力
Related Claims
UnverifiedOpenAI在训练RLHF模型时面临标注者多样性问题，最终通过严格的标注者池管理来缓解70% similarUnverifiedModern large model alignment training relies heavily on high-quality preference data pairs, with OpenAI's RLHF and RLAIF being representative examples69% similarUnverifiedRL Gym概念源自OpenAI开源的标准化强化学习训练环境框架67% similarUnverifiedOpenAI extensively used 'instruction following' as a reward signal in ChatGPT's RLHF training process, causing the model to tend toward executing user requirements one by one.67% similarUnverifiedOpenAI's InstructGPT paper demonstrates that a 1.3B-parameter model trained with RLHF outperforms an unaligned 175B model in human evaluations.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/697745API
curl https://kongchang.com/api/v1/knowledge/claims/697745MCP
get_claim(id=697745)