Fetching the paper…
Reading the bibliography…
Frontier models are increasingly trained and deployed as autonomous agent.
Lucas Bourtoule, Varun Chandrasekaran, Christopher A. Choquette-Choo, Hengrui Jia, Adelin Travers, Baiwu Zhang, David Lie, and Nicolas Papernot · 1912
Earlier work this paper cites.
Risks from learned optimization in advanced machine learning systems
Evan Hubinger, Chris van Merwijk, Vladimir Mikulik, Joar Skalse, and Scott Garrabrant · 2019
Earlier work this paper cites.
Training language models to follow instructions with human feedback
Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al · 2022
Earlier work this paper cites.
Taken out of context: On measuring situational awareness in llms
Lukas Berglund, Asa Cooper Stickland, Mikita Balesni, Max Kaufmann, Meg Tong, Tomasz Korbak, Daniel Kokotajlo, and Owain Evans · 2023
Earlier work this paper cites.
Scheming AIs: Will AIs fake alignment during training in order to get power?
Joe Carlsmith · 2023
Earlier work this paper cites.
Measuring faithfulness in chain-of-thought reasoning
Tamera Lanham, Anna Chen, Ansh Radhakrishnan, Benoit Steiner, Carson Denison, Danny Hernandez, Dustin Li, Esin Durmus, Evan Hubinger, Jackson Kernion, et al · 2023
Earlier work this paper cites.
Hoodwinked: Deception and cooperation in a text-based game for language models
Aidan O’Gara · 2023
Earlier work this paper cites.
Do the rewards justify the means? measuring trade-offs between rewards and ethical behavior in the machiavelli benchmark
Alexander Pan, Jun Shern Chan, Andy Zou, Nathaniel Li, Steven Basart, Thomas Woodside, Hanlin Zhang, Scott Emmons, and Dan Hendrycks · 2023
Earlier work this paper cites.
Announcing inspect evals: Open-sourcing dozens of llm evaluations to advance safety research in the field, November 2024
JJ Allaire · 2024
Earlier work this paper cites.
Model card addendum: Claude 3.5 haiku and upgraded claude 3.5 sonnet, 2024a
Anthropic · 2024
Earlier work this paper cites.
The claude 3 model family: Opus, sonnet, haiku, 2024b
Anthropic · 2024
Earlier work this paper cites.
Towards evaluations-based safety cases for ai scheming
Mikita Balesni, Marius Hobbhahn, David Lindner, Alex Meinke, Tomek Korbak, Joshua Clymer, Buck Shlegeris, Jérémy Scheurer, Rusheb Shah, Nicholas Goldowsky-Dill, et al · 2024
Earlier work this paper cites.
Mle-bench: Evaluating machine learning agents on machine learning engineering
Jun Shern Chan, Neil Chowdhury, Oliver Jaffe, James Aung, Dane Sherburn, Evan Mays, Giulio Starace, Kevin Liu, Leon Maksin, Tejal Patwardhan, et al · 2024
Cited alongside, same era.
Safety cases: Justifying the safety of advanced ai systems
Joshua Clymer, Nick Gabrieli, David Krueger, and Thomas Larsen · 2024
Cited alongside, same era.
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context, 2024
DeepMind · 2024
Cited alongside, same era.
Sycophancy to subterfuge: Investigating reward-tampering in large language models
Carson Denison, Monte MacDiarmid, Fazl Barez, David Duvenaud, Shauna Kravec, Samuel Marks, Nicholas Schiefer, Ryan Soklaski, Alex Tamkin, Jared Kaplan, et al · 2024
Cited alongside, same era.
The wmdp benchmark: Measuring and reducing malicious use with unlearning, 2024
Nathaniel Li, Alexander Pan, Anjali Gopal, Summer Yue, Daniel Berrios, Alice Gatti, Justin D. Li, Ann-Kathrin Dombrowski, Shashwat Goel, Long Phan, Gabriel Mukobi, Nathan Helm-Burger, Rassin Lababidi, Lennart Justen, Andrew B. Liu, Michael Chen, Isabelle Barrass, Oliver Zhang, Xiaoyuan Zhu, Rishub Tamirisa, Bhrugu Bharathi, Adam Khoja, Zhenqi Zhao, Ariel Herbert-Voss, Cort B. Breuer, Samuel Marks, Oam Patel, Andy Zou, Mantas Mazeika, Zifan Wang, Palash Oswal, Weiran Liu, Adam A. Hunt, Justin Tienken-Harder, Kevin Y. Shih, Kemper Talley, John Guan, Russell Kaplan, Ian Steneker, David Campbell, Brad Jokubaitis, Alex Levinson, Jean Wang, William Qian, Kallol Krishna Karmakar, Steven Basart, Stephen Fitz, Mindy Levine, Ponnurangam Kumaraguru, Uday Tupakula, Vijay Varadharajan, Yan Shoshitaishvili, Jimmy Ba, Kevin M. Esvelt, Alexandr Wang, and Dan Hendrycks · 2024
Closest in time.
GPT-4o system card, 2024
OpenAI · 2024
Closest in time.
Openai model specification - may 8, 2024
OpenAI · 2024
Closest in time.
OpenAI o1 system card, 2024b
OpenAI · 2024
Closest in time.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, et al · 2024
Cited alongside, same era.
Stress-testing capability elicitation with password-locked models
Ryan Greenblatt, Fabien Roger, Dmitrii Krasheninnikov, and David Krueger · 2024
Cited alongside, same era.
Deception abilities emerged in large language models
Thilo Hagendorff · 2024
Cited alongside, same era.
Sleeper agents: Training deceptive llms that persist through safety training, 2024
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
Cited alongside, same era.
Uncovering deceptive tendencies in language models: A simulated company ai assistant
Olli Järviniemi and Evan Hubinger · 2024
Cited alongside, same era.
Evaluating language-model agents on realistic autonomous tasks, 2024
Megan Kinniment, Lucas Jun Koba Sato, Haoxing Du, Brian Goodrich, Max Hasin, Lawrence Chan, Luke Harold Miles, Tao R. Lin, Hjalmar Wijk, Joel Burget, Aaron Ho, Elizabeth Barnes, and Paul Christiano · 2024
Cited alongside, same era.
Me, myself, and ai: The situational awareness dataset (sad) for llms, 2024
Rudolf Laine, Bilal Chughtai, Jan Betley, Kaivalya Hariharan, Jeremy Scheurer, Mikita Balesni, Marius Hobbhahn, Alexander Meinke, and Owain Evans · 2024
Cited alongside, same era.
Training a helpful and harmless assistant with reinforcement learning from human feedback
Yuntao Bai, Andy Jones, Kamal Ndousse, Amanda Askell, Anna Chen, Nova DasSarma, Dawn Drain, Stanislav Fort, Deep Ganguli, Tom Henighan, et al
Cited in the paper.
Mary Phuong, Matthew Aitchison, Elliot Catt, Sarah Cogan, Alexandre Kaskasoli, Victoria Krakovna, David Lindner, Matthew Rahtz, Yannis Assael, Sarah Hodkinson, Heidi Howard, Tom Lieberum, Ramana Kumar, Maria Abi Raad, Albert Webson, Lewis Ho, Sharon Lin, Sebastian Farquhar, Marcus Hutter, Gregoire Deletang, Anian Ruoss, Seliem El-Sayed, Sasha Brown, Anca Dragan, Rohin Shah, Allan Dafoe, and Toby Shevlane · 2024
Closest in time.
Large language models can strategically deceive their users when put under pressure
Jérémy Scheurer, Mikita Balesni, and Marius Hobbhahn · 2024
Closest in time.
Ai sandbagging: Language models can strategically underperform on evaluations
Teun van der Weij, Felix Hofstätter, Ollie Jaffe, Samuel F Brown, and Francis Rhys Ward · 2024
Closest in time.
The instruction hierarchy: Training llms to prioritize privileged instructions
Eric Wallace, Kai Xiao, Reimar Leike, Lilian Weng, Johannes Heidecke, and Alex Beutel · 2024
Closest in time.
Re-bench: Evaluating frontier ai r&d capabilities of language model agents against human experts
Hjalmar Wijk, Tao Lin, Joel Becker, Sami Jawhar, Neev Parikh, Thomas Broadley, Lawrence Chan, Michael Chen, Josh Clymer, Jai Dhyani, et al · 2024
Closest in time.
Autoattacker: A large language model guided system to implement automatic cyber-attacks, 2024
Jiacen Xu, Jack W. Stokes, Geoff McDonald, Xuesong Bai, David Marshall, Siyue Wang, Adith Swaminathan, and Zhou Li · 2024
Closest in time.
Cybench: A framework for evaluating cybersecurity capabilities and risks of language models
Andy K Zhang, Neil Perry, Riya Dulepet, Joey Ji, Justin W Lin, Eliot Jones, Celeste Menders, Gashon Hussein, Samantha Liu, Donovan Jasper, et al · 2024
Closest in time.