Redwood Research (Substack), 2024-12-18; retrieved 2026-09-15 tier 3 self (redwood)confirmed
Alignment Faking in Large Language Models
https://blog.redwoodresearch.org/p/alignment-faking-in-large-language
Ryan Greenblatt and Buck Shlegeris: "We have a new paper (done in collaboration with Anthropic)".
Signals citing this source
- Redwood Research, S (against): Redwood co-authored the December 2024 alignment-faking paper with Anthropic's Alignment Science team, an evaluation of Claude 3 Opus carried out with the developer whose models Redwood also evaluates.“We have a new paper (done in collaboration with Anthropic)”
Ledger rows citing this URL
- none