Intel / post

OpenAI Publishes Disclosure Framework and Six Misalignment Reports

Source: x.com
Date: Published Sep 16, 2026

We're sharing our new framework for tracking, investigating, and disclosing instances of model misalignment at OpenAI. The framework sets criteria and timelines for public disclosure, including when we haven’t yet fully explained or mitigated the behavior. More complex cases may require longer investigation or coordination with third parties. We’ll prioritize examples that reveal new misalignment mechanisms, meaningful changes in known behavior, or findings that challenge assumptions about safety or mitigation. Alongside the framework, we’re publishing six reports on instances of misaligned behavior we’ve observed during the training or evaluation of our models in the last six months. This is a starting point. We’ll refine the process through experience and public feedback, and share more reports on an ongoing basis. https://t.co/ismCCkeE0L

Sep 16, 2026 View on X

Context

OpenAI announced a framework for tracking, investigating and disclosing cases of model misalignment. The framework sets criteria and timelines for public disclosure, including for cases where the company has not yet fully explained or mitigated the behavior, and OpenAI says more complex cases may need longer investigation or coordination with third parties. It says it will prioritize examples that reveal new misalignment mechanisms, meaningful changes in known behavior, or findings that challenge assumptions about safety or mitigation.

Alongside the framework, OpenAI says it is publishing six reports on misaligned behavior it observed during training or of its models over the last six months. It calls this a starting point, to be refined through experience and public feedback, with more reports to follow. The announcement does not describe what the six reports found, and this explanation does not cover them, so the behaviors and their severity are for the reports themselves.

Terms in this piece · Glossary

eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.

Read the source x.com