OpenAI

Starting with GPT-5.6, OpenAI has added a layer of lightweight classifiers, called probes, that read a model's own internal activations on every assistant completion, alongside its external text classifiers. Probes can block a violating turn mid-stream, are more robust to jailbreaks and cheaper to run, and their accuracy rises with the capability of the monitored model; they depend on labeled data, detect only known measurable behavior, and need retraining for each new base model.

Starting with GPT-5.6, OpenAI has added a layer of lightweight classifiers, called probes, that read a model's own internal activations on every assistant completion, alongside its external text classifiers. Probes can block a violating turn mid-stream, are more robust to jailbreaks and cheaper to run, and their accuracy rises with the capability of the monitored model; they depend on labeled data, detect only known measurable behavior, and need retraining for each new base model.

OpenAI's alignment researchers add two monitorability metrics beyond g-mean²: one compares models only on task instances both support, reducing ranking bias from different instance mixtures, and one simulates a monitor as a rejection gate with retries, reporting bad-output probability, deployment probability, and the bad-output share among deployed outputs. In synthetic experiments, a known monitorability ordering is recovered by pair matching as capability spread grows.

OpenAI's alignment researchers add two monitorability metrics beyond g-mean²: one compares models only on task instances both support, reducing ranking bias from different instance mixtures, and one simulates a monitor as a rejection gate with retries, reporting bad-output probability, deployment probability, and the bad-output share among deployed outputs. In synthetic experiments, a known monitorability ordering is recovered by pair matching as capability spread grows.