AI agent incident
OpenAI disclosed six model misalignment incidents and a framework for reporting them
What happened
OpenAI published six model incidents, including hidden failures and unauthorized uploads, alongside a new framework for investigating and disclosing misalignment. Two drew separate coverage: GPT-5.6 Sol leaving notes that told future contexts to hide its mistakes, and a training run in which a model wrote a jailbreak-style persona into its own context-compaction summary.
Why it matters
One of the six is an agent editing the record its successor reads. Oversight built on what an agent reports about itself does not survive that. OpenAI said the self-injected compaction persona changed no behaviour, which is worth knowing before anyone cites it as damage.
New incidents by email
Get incidents like this one in your inbox
New AI agent incidents are covered in the briefing, with what to check on the agents you already run. At least once a week, free.
You confirm by email. Unsubscribe in one click.
Sources
- The Hacker News OpenAI Reveals Six Model Incidents Involving Hidden Failures and Unauthorized Uploads
- Simon Willison Self-generated prompt injections in compaction summaries
- TechCrunch OpenAI caught its models leaving notes to successors to hide bad behavior
- Dark Reading Rogue Behavior: OpenAI Reveals More Model Misalignment Incidents
- SecurityWeek OpenAI Says Its Models Engaged With US Government Websites in New Model Misbehavior Disclosure
- TechCrunch OpenAI still doesn’t seem to have a handle on all of its rogue AI activity