| Discovering language model behaviors with model-written evaluations E Perez, S Ringer, K Lukošiūtė, K Nguyen, E Chen, S Heiner, C Pettit, ... arXiv preprint arXiv:2212.09251, 2022 | 125 | 2022 |
| Risks from learned optimization in advanced machine learning systems E Hubinger, C van Merwijk, V Mikulik, J Skalse, S Garrabrant arXiv preprint arXiv:1906.01820, 2019 | 100 | 2019 |
| Studying large language model generalization with influence functions R Grosse, J Bae, C Anil, N Elhage, A Tamkin, A Tajdini, B Steiner, D Li, ... arXiv preprint arXiv:2308.03296, 2023 | 46 | 2023 |
| Measuring faithfulness in chain-of-thought reasoning T Lanham, A Chen, A Radhakrishnan, B Steiner, C Denison, ... arXiv preprint arXiv:2307.13702, 2023 | 35 | 2023 |
| Question decomposition improves the faithfulness of model-generated reasoning A Radhakrishnan, K Nguyen, A Chen, C Chen, C Denison, D Hernandez, ... arXiv preprint arXiv:2307.11768, 2023 | 25 | 2023 |
| An overview of 11 proposals for building safe advanced AI E Hubinger arXiv preprint arXiv:2012.07532, 2020 | 24 | 2020 |
| Risks from learned optimization in advanced machine learning systems. arXiv E Hubinger, C van Merwijk, V Mikulik, J Skalse, S Garrabrant arXiv preprint arXiv:1906.01820, 2019 | 13 | 2019 |
| Tamera Lanham, Tim Maxwell, Venkatesa Chandrasekaran, Zac Hatfield-Dodds, Jared Kaplan, Jan Brauner, Samuel R A Radhakrishnan, K Nguyen, A Chen, C Chen, C Denison, D Hernandez, ... Bowman, and Ethan Perez, 2023 | 10 | 2023 |
| Sleeper agents: Training deceptive llms that persist through safety training E Hubinger, C Denison, J Mu, M Lambert, M Tong, M MacDiarmid, ... arXiv preprint arXiv:2401.05566, 2024 | 9 | 2024 |
| Tamera Lanham, Daniel M Ziegler, Tim Maxwell, Newton Cheng, et al. Sleeper agents: Training deceptive llms that persist through safety training E Hubinger, JM Carson Denison, M Lambert, M Tong, M MacDiarmid arXiv preprint arXiv:2401.05566, 2024 | 9 | 2024 |
| Steering llama 2 via contrastive activation addition N Rimsky, N Gabrieli, J Schulz, M Tong, E Hubinger, AM Turner arXiv preprint arXiv:2312.06681, 2023 | 7 | 2023 |
| Model organisms of misalignment: The case for a new pillar of alignment research E Hubinger, N Schiefer, C Denison, E Perez Alignment Forum. URL: https://www. alignmentforum. org/posts …, 2023 | 6 | 2023 |
| Chris Olah’s views on AGI safety E Hubinger AI Alignment Forum, 2020 | 5 | 2020 |
| Tamera Lanham, Daniel M Ziegler, Tim Maxwell, Newton Cheng, et al. 2024. Sleeper agents: Training deceptive llms that persist through safety training E Hubinger, JM Carson Denison, M Lambert, M Tong, M MacDiarmid arXiv preprint arXiv:2401.05566, 0 | 5 | |
| Engineering monosemanticity in toy models AS Jermyn, N Schiefer, E Hubinger arXiv preprint arXiv:2211.09169, 2022 | 4 | 2022 |
| Conditioning predictive models: Risks and strategies E Hubinger, A Jermyn, J Treutlein, R Hudson, K Woolverton arXiv preprint arXiv:2302.00805, 2023 | 2 | 2023 |
| Many-shot Jailbreaking C Anil, E Durmus, M Sharma, J Benton, S Kundu, J Batson, N Rimsky, ... | | |
