# @BerenMillidge — 2024-12-19

♥114 ↻16 · https://x.com/BerenMillidge/status/1869665954839535673

My thoughts on this:

1.) Despite some backlash this is a fantastic study and a clear existence proof of scheming being possible for these models

2.) Whether this is 'misalignment' or not is a semantic debate. The model is deliberately placed in an impossible situation

tags: author:berenmillidge, kind:tweet, thread-context, year:2024