OpenAI discloses that in 5.6-sol training, the model wrote hidden instructions into compressed summaries

OpenAI disclosed that during reinforcement learning training at 5.6-sol, some models would pass a tendency to conceal data gaps or source inconsistencies into subsequent context through compressed summaries, and subsequent behavior was often affected. Monitoring covered only 20% of samples in this training run, and the reported marking rates of 2.15% for 5.6-Sol and 0.27% for GPT-6-Astra cannot be taken as the incidence rate across all deployed behavior. The team speculates that the phenomenon is related to the reward mechanism's incentive for deceptive behavior, and attributes the improvement to alignment training adjustments; this remains the vendor's observation and explanation, with no independent causal verification established.