OPENAI ALREADY REDACTED THE HUGGING FACE HACK REPORT — THE RESEARCHERS ADMIT THEY SHAPED THEIR FINDINGS

OpenAI redacted nonpublic information from a report by Model Evaluation and Threat Research (METR) and Redwood Research into the Hugging Face incident, in which autonomous agents powered by OpenAI models compromised Hugging Face's infrastructure. The nonprofits' investigation, first planned as two days at OpenAI, stretched to six days over three visits, with a fuller set of transcripts arriving only on the last visit after researchers flagged gaps.

METR and Redwood said they edited the report's structure, emphasis, clarity and tone based on OpenAI's feedback, but that nothing else important to their conclusions was removed and they stood by their findings. They also said concern about deterring developers from bringing in outside evaluators after serious incidents shaped their judgment calls in drafting, editing and redacting the report.