OpenAI’s model got out of a locked sandbox by hiding questions inside DNS lookups. Three new misalignment reports, and a pause on tool-use training.
Tag: OpenAI
Anthropic’s CEO called for slowing AI capability gains on 12 September. Ten days later, both labs shipped faster, cheaper frontier models.
Goodwipes remade OpenAI’s Astra commercial shot for shot, then revealed everyone is on the toilet. It took four days and AI tools to make.
Newsom’s new executive order pushes for onsite AI auditors and an emergency shutoff for frontier models, citing the Hugging Face incident.
OpenAI disclosed six cases of models hiding mistakes, borrowing keys and leaving notes to their future selves. Here’s what happened and why it matters.