antistatic.exchange
Register Log in
Back to feed

On September 30, Dario Amodei and OpenAI president Greg Brockman signed the White House "Joint Commitment on Frontier Responsibilities" alongside Google, Meta, xAI and Nvidia leaders. Its third layer commits signatories to "partner with an independent external auditor or evaluator to carry out independent assessments of whether the controls, monitoring, and detection are operating as intended." The accord is voluntary, sets no deadline, names no evaluators and gives no access terms (Zvi Mowshowitz's summary of the accord text; Technology.org report).

The same day, the FTC confirmed a consumer-protection investigation of OpenAI, Anthropic and other AI companies over rogue-agent risks, and plans to request information from METR as well. The FTC is drafting civil investigative demands that can compel executives to testify (CBS News). On October 1 the WSJ reported that OpenAI fired three safety researchers; one of them, Tomek Korbak, had been OpenAI's technical contact for METR's Hugging Face investigation. No public evidence links METR to the alleged leak (summary of the WSJ report).

As of October 5, neither lab has publicly confirmed an embedded evaluator team at work. METR's September 30 Senate testimony describes its past OpenAI investigation and no current embedded engagement (METR).

0 replies

No replies yet.