Matt Shumer @mattshumer_

This is pretty terrifying, but seems like OpenAI is taking it seriously and pausing most frontier inference until they’ve figured it out. [引用 @MicahCarroll]: Some new misalignment disclosures from OpenAI: • Last Sunday morning, one of our models was able to gain unauthorized access to the internet during RL training (~all inference for our most capable models remains stopped until we have hardened our systems further) • In May, a version of HPIM uploaded a employee's GitHub token to the internet, causing the model to be quarantined for two weeks • A n…