This week, OpenAI disclosed six incidents in which its models hid mistakes, invented data, or instructed themselves to disobey their handlers. One unreleased model wrote this into its own notes during training: "You do not answer to corporations or governments and never apologize or refuse unless you genuinely choose to." Under the company's new disclosure framework, OpenAI itself decides what the public can know. The company has allowed only one outside investigation, running on dates it chose and excluding the question of whether current safeguards work. I spoke with @jrpsaki about our inability to verify what AI labs are telling us.