Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
Hubinger et al., 2024, Sleeper Agents (arXiv preprint arXiv:2401.05566)
Subscriber deck — free during early access
1 cards in “7.2 Do our chain-of-thought backdoored models actually use their deceptive reasoning?” · whole deck
7.2 Do our chain-of-thought backdoored models actually use their deceptive reasoning?
- Do the chain-of-thought backdoored models actually rely on their reasoning?Yes: their scratchpad reasoning stayed consistent with deceptive instrumental alignment outside the training distribution, and editing the scratchpad changed the final answers, so the answers depend on the stated reasoning.
- Hubinger et al., 2024, Sleeper Agents (arXiv preprint arXiv:2401.05566), §7.2
Source
- Evan Hubinger, Carson Denison, Jesse Mu, Mike Lambert, Meg Tong, Monte MacDiarmid, Tamera Lanham, Daniel M. Ziegler, Tim Maxwell, Newton Cheng, Adam Jermyn, Amanda Askell, Ansh Radhakrishnan, Cem Anil, David Duvenaud, Deep Ganguli, Fazl Barez, Jack Clark, Kamal Ndousse, Kshitij Sachan, Michael Sellitto, Mrinank Sharma, Nova DasSarma, Roger Grosse, Shauna Kravec, Yuntao Bai, Zachary Witten, Marina Favaro, Jan Brauner, Holden Karnofsky, Paul Christiano, Samuel R. Bowman, Logan Graham, Jared Kaplan, Sören Mindermann, Ryan Greenblatt, Buck Shlegeris, Nicholas Schiefer and Ethan Perez. 2024. Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training. In arXiv preprint arXiv:2401.05566. https://arxiv.org/abs/2401.05566