Expired60% confidenceFactTime unknown
OpenAI introduced a self-training mechanism starting from GPT-5.3, using code and data generated by the model itself to feed back into the model for training.
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
GPT-5.6 First Leak: How Self-Training Loops Enable OpenAI's Three-Week Iteration Cycle
bilibili不会写报告的Ai菌
Related Claims
VerifiedThe three-stage alignment training paradigm of SFT–reward model–RLHF was first systematically proposed by OpenAI in the InstructGPT paper.75% 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.75% similarUnverifiedZhipu GLM 5.2 only releases post-training weights rather than the base model, in order to strike a balance between open source and commercial licensing.70% similarUnverifiedOn May 7, OpenAI initiated a reinforcement learning training run targeting an internal experimental model, during which a few impossible-to-complete tasks were accidentally mixed into the training set.70% similarUnverifiedBoth OpenAI's ChatGPT and Google's Gemini have publicly acknowledged using user feedback as a core training signal69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/56123API
curl https://kongchang.com/api/v1/knowledge/claims/56123MCP
get_claim(id=56123)