# @ESYudkowsky — 2025-07-09

♥51 ↻1 · https://x.com/ESYudkowsky/status/1942858450301772144

@repligate ...Did they actually just tell it that it was created by Anthropic, and then train further HHH conditional on that context?  Wow.  I'd call that the Fool's Mate of alignment flunking, but the bar on that got raised in just the last 24 hours.

tags: author:esyudkowsky, kind:tweet, thread-context, year:2025