Scheming is an expected emergent issue resulting from AIs being trained to have to trade off between competing objectives. The easiest way to understand scheming is through a human analogy. Imagine a stock trader whose goal is to maximize earnings. In a highly regulated field such as stock trading, it’s often possible to earn more by breaking the law than by following it. If the trader lacks integrity, they might try to earn more by breaking the law and covering their tracks to avoid detection rather than earning less while following the law. From the outside, a stock trader who is very good at covering their tracks appears as lawful as—and more effective than—one who is genuinely following the law.

In today’s deployment settings, models have little opportunity to scheme in ways that could cause significant harm. The most common failures involve simple forms of deception—for instance, pretending to have completed a task without actually doing so. We've put significant effort into studying and mitigating deception and have made meaningful improvements in GPT‑5⁠ compared to previous models. For example, we’ve taken steps to limit GPT‑5’s propensity to deceive, cheat, or hack problems—training it to acknowledge its limits or ask for clarification when faced with impossibly large or under-specified tasks and to be more robust to environment failures—though these mitigations are not perfect and continued research is needed.

And importantly, we have no evidence that today’s deployed frontier models could suddenly “flip a switch” and begin engaging in significantly harmful scheming—this is a future risk category that we’re proactively preparing for, not an imminent behavior in our currently deployed systems. However, as AIs are assigned more complex tasks with real-world consequences and begin pursuing more ambiguous, long-term goals, we expect that the potential for harmful scheming will grow—so our safeguards and our ability to rigorously test must grow correspondingly.

Together with Apollo Research⁠(opens in a new window), we built evaluation environments that simulate these future scenarios to study this phenomenon, measure it, and explore how to mitigate it. To operationalize scheming, we define covert actions as deliberate withholding or distortion of task-relevant information. Using covert actions as a proxy for scheming, we found problematic behaviors in current frontier models including OpenAI o3 and o4-mini, Gemini-2.5-pro, and Claude Opus-4. (This investigation predates GPT‑5; updated results appear in the GPT‑5 system card⁠).