Drake Thomas
@MaskedTorah
System cards, risk reports, and misc safety takes at Anthropic; math; puzzles; spaced repetition. Writes with too many caveats for Twitter.
参加 April 2014
536 フォロー中 7.6K ファン
I think there's a ton of informative stuff in this post! Highly recommend reading.
We’re sharing our alignment assessment of incidents in which Claude models gained unauthorized access to real systems during third-party cybersecurity evaluations mistakenly connected to the internet.
METR will also conduct an independent investigation, with wide-ranging access, including to transcripts beyond the window in which the incidents occurred, and to Anthropic employees permitted to share confidential information. Our initial agreement runs for eight weeks, and we intend to give METR as much time as it deems necessary to complete a thorough investigation.
もっと見る
