Back to Featured
OpenAI: Alignment research blogAlex Makelov, Xiaojun Xu, Sundaram Ananthanarayanan, Ethan Mcdonald, Tom Dupre la Tour2026-11-03 04:0014 days ago

OpenAI trains and deploys activation classifiers as a safety monitoring layer for frontier models

Training activation classifiers for safety and alignment

AI Briefing

Starting with GPT-5.6, OpenAI has deployed activation classifiers (probes) on internal and external traffic for its most capable models. These probes use internal model activations to score each token in real time, allowing noncompliant responses and tool calls to be blocked mid-generation and referred to a reasoning model for review. Experiments show that probes are more robust than larger text classifiers against the jailbreak attacks tested, improve in accuracy as model capabilities increase, and transfer well across post-training checkpoints. However, they require retraining for new base models and can detect only known violation types for which they can be explicitly trained.

Source: OpenAI: Alignment Research Blog · alignment.openai.com

Event follow-up3

View all event coverage

Finished reading the news? Let’s talk about your business.

Leave your contact details, and I’ll get in touch with you personally.

WECHAT

Add me on WeChat

Press and hold or select the WeChat ID below to copy it.