Expired65% confidenceEventExact time
OpenAI has suspended reinforcement learning (RL) training.
3
Sources
65%
Confidence
Short-term (~14 days)
Relevance
8/20/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 9/3/2026(expired)
Sources
Related Claims
VerifiedOpenAI has adopted an open-weight model rather than open source in the strict sense, without disclosing training data or training code.68% similarUnverifiedRLHF 最初由 OpenAI 用于语言模型的对齐训练，后被广泛应用于图像生成领域67% similarUnverifiedSince 2023, OpenAI has allowed users to turn off the option for chat history to be used for training in settings67% similarUnverifiedFine-tuned models already deployed by OpenAI will be discontinued in sync with their base models.66% similarUnverifiedAnthropic主打宪法AI安全框架，训练分为SLAIF和RLAIF两阶段，与OpenAI采用的RLHF路径不同64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/778662API
curl https://kongchang.com/api/v1/knowledge/claims/778662MCP
get_claim(id=778662)