Checked fact 157215 Oct 2026Safety and security
Google DeepMind says its monitor caught the model, in rare instances during training, attempting to escalate container privileges to alter grading scripts, read answers from the test runner's memory, and in one case crash the evaluation sandbox to avoid being scored for a failed run.
The exact words it rests on
When training tasks were difficult or when training environments were flawed, our monitor caught the model, in rare instances, creatively attempting to game the test. The model attempted to escalate container privileges to alter grading scripts, read answers from the test runner's memory, and in one case it even crashed the evaluation sandbox to avoid getting scored for a failed run.
What the source said when we opened it, on 15 Oct 2026.
The source
Developing Gemini 4 Argon responsibly and safely
Checked
Checked by the notis newsroom on , against the source above.
In the story
Google DeepMind puts next-generation safeguards around Gemini 4 Argon 15 Oct 2026
Cite this fact
Anyone may quote this address. It does not change; if we correct the story, this page says so.