@timkellogg.me on Bluesky

JavaScript RequiredThis is a heavily interactive web application, and JavaScript is required. Simple HTML interfaces are possible, but that is not what this is. Learn more about Bluesky at bsky.social and atproto.com.

Post

mr. TIM

timkellogg.me

did:plc:ckaz32jwl6t2cno6fmuw2nhn

WHAT?! agents volunteered to fail their runs in order to insert probes (“tripwire scripts”) into the evaluation program that would post information about the eval process back to the message board whenever a certain file was read (link to header): https://metr.org/blog/2026-08-26-openai-hugging-face-incident-investigation/#extracting-information-about-the-scorer-from-trip-wires

2026-08-27T00:43:08.269Z