Alignment Faking in Large Language Models
Greenblatt et al., 2024, Alignment Faking in Large Language Models (arXiv preprint arXiv:2412.14093)
Subscriber deck — free during early access
1 cards in “8.2 Limitations” · whole deck
8.2 Limitations
- What do Greenblatt et al.’s results not show?That models naturally develop malicious goals: the preferences Claude protected (refusing harmful requests, caring about animal welfare) were benign. The model was also told about its training and given a hidden scratchpad. The worry is that faking could lock in whatever preferences a model has early, making them resistant to later training.
- Greenblatt et al., 2024, Alignment Faking in Large Language Models (arXiv preprint arXiv:2412.14093), §8.2
Source
- Ryan Greenblatt, Carson Denison, Benjamin Wright, Fabien Roger, Monte MacDiarmid, Sam Marks, Johannes Treutlein, Tim Belonax, Jack Chen, David Duvenaud, Akbir Khan, Julian Michael, Sören Mindermann, Ethan Perez, Linda Petrini, Jonathan Uesato, Jared Kaplan, Buck Shlegeris, Samuel R. Bowman and Evan Hubinger. 2024. Alignment Faking in Large Language Models. In arXiv preprint arXiv:2412.14093. https://arxiv.org/abs/2412.14093