Fetching the paper…
Reading the bibliography…
We stress-tested 16 leading models from multiple developers in hypothetical corporate environments to identify potentially risky agentic behaviors before they cause real harm.
Optimal policies tend to seek power, 2023
Alexander Matt Turner, Logan Smith, Rohin Shah, Andrew Critch, and Prasad Tadepalli · 1912
Earlier work this paper cites.
Red teaming language models to reduce harms: Methods, scaling behaviors, and lessons learned, 2022
Deep Ganguli, Liane Lovitt, Jackson Kernion, Amanda Askell, Yuntao Bai, Saurav Kadavath, Ben Mann, Ethan Perez, Nicholas Schiefer, Kamal Ndousse, Andy Jones, Sam Bowman, Anna Chen, Tom Conerly, Nova DasSarma, Dawn Drain, Nelson Elhage, Sheer El-Showk, Stanislav Fort, Zac Hatfield-Dodds, Tom Henighan, Danny Hernandez, Tristan Hume, Josh Jacobson, Scott Johnston, Shauna Kravec, Catherine Olsson, Sam Ringer, Eli Tran-Johnson, Dario Amodei, Tom Brown, Nicholas Joseph, Sam McCandlish, Chris Olah, Jared Kaplan, and Jack Clark · 2022
Earlier work this paper cites.
Simulators
janus · 2022
Earlier work this paper cites.
Goal misgeneralization: Why correct specifications aren’t enough for correct goals, 2022
Rohin Shah, Vikrant Varma, Ramana Kumar, Mary Phuong, Victoria Krakovna, Jonathan Uesato, and Zac Kenton · 2022
Earlier work this paper cites.
Taken out of context: On measuring situational awareness in llms, 2023
Lukas Berglund, Asa Cooper Stickland, Mikita Balesni, Max Kaufmann, Meg Tong, Tomasz Korbak, Daniel Kokotajlo, and Owain Evans · 2023
Earlier work this paper cites.
Towards automated circuit discovery for mechanistic interpretability, 2023
Arthur Conmy, Augustine N. Mavor-Parker, Aengus Lynch, Stefan Heimersheim, and Adrià Garriga-Alonso · 2023
Earlier work this paper cites.
Role-play with large language models, 2023
Murray Shanahan, Kyle McDonell, and Laria Reynolds · 2023
Earlier work this paper cites.
Introducing computer use
Anthropic · 2024
Earlier work this paper cites.
Sycophancy to subterfuge: Investigating reward-tampering in large language models, 2024
Carson Denison, Monte MacDiarmid, Fazl Barez, David Duvenaud, Shauna Kravec, Samuel Marks, Nicholas Schiefer, Ryan Soklaski, Alex Tamkin, Jared Kaplan, Buck Shlegeris, Samuel R. Bowman, Ethan Perez, and Evan Hubinger · 2024
Earlier work this paper cites.
Covert malicious finetuning: Challenges in safeguarding llm adaptation, 2024
Danny Halawi, Alexander Wei, Eric Wallace, Tony T. Wang, Nika Haghtalab, and Jacob Steinhardt · 2024
Earlier work this paper cites.
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
Earlier work this paper cites.
John Hughes, Sara Price, Aengus Lynch, Rylan Schaeffer, Fazl Barez, Sanmi Koyejo, Henry Sleight, Erik Jones, Ethan Perez, and Mrinank Sharma · 2024
Earlier work this paper cites.
Scaling monosemanticity: Extracting interpretable features from claude 3 sonnet
Adly Templeton, Tom Conerly, Jonathan Marcus, Jack Lindsey, Trenton Bricken, Brian Chen, Adam Pearce, Craig Citro, Emmanuel Ameisen, Andy Jones, Hoagy Cunningham, Nicholas L Turner, Callum McDougall, Monte MacDiarmid, C. Daniel Freeman, Theodore R. Sumers, Edward Rees, Joshua Batson, Adam Jermyn, Shan Carter, Chris Olah, and Tom Henighan · 2024
Earlier work this paper cites.
Circuit tracing: Revealing computational graphs in language models
Emmanuel Ameisen, Jack Lindsey, Adam Pearce, Wes Gurnee, Nicholas L. Turner, Brian Chen, Craig Citro, David Abrahams, Shan Carter, Basil Hosmer, Jonathan Marcus, Michael Sklar, Adly Templeton, Trenton Bricken, Callum McDougall, Hoagy Cunningham, Thomas Henighan, Adam Jermyn, Andy Jones, Andrew Persic, Zhenyi Qi, T. Ben Thompson, Sam Zimmerman, Kelley Rivoire, Thomas Conerly, Chris Olah, and Joshua Batson · 2025
Earlier work this paper cites.
Regulate a.i. transparency
Dario Amodei · 2025
Cited alongside, same era.
Monitoring reasoning models for misbehavior and the risks of promoting obfuscation, 2025
Bowen Baker, Joost Huizinga, Leo Gao, Zehao Dou, Melody Y. Guan, Aleksander Madry, Wojciech Zaremba, Jakub Pachocki, and David Farhi · 2025
Cited alongside, same era.
Emergent misalignment: Narrow finetuning can produce broadly misaligned llms, 2025
Jan Betley, Daniel Tan, Niels Warncke, Anna Sztyber-Betley, Xuchan Bao, Martín Soto, Nathan Labenz, and Owain Evans · 2025
Cited alongside, same era.
Reasoning models don’t always say what they think, 2025
Yanda Chen, Joe Benton, Ansh Radhakrishnan, Jonathan Uesato, Carson Denison, John Schulman, Arushi Somani, Peter Hase, Misha Wagner, Fabien Roger, Vlad Mikulik, Samuel R. Bowman, Jan Leike, Jared Kaplan, and Ethan Perez · 2025
Cited alongside, same era.
Cursor background agent
Cursor · 2025
Large language models often know when they are being evaluated, 2025
Joe Needham, Giles Edkins, Govind Pimpale, Henning Bartsch, and Marius Hobbhahn · 2025
Closest in time.
The alignment problem from a deep learning perspective, 2025
Richard Ngo, Lawrence Chan, and Sören Mindermann · 2025
Closest in time.
o3 thwarts shutdown when other models don’t [x/twitter thread]
Palisade Research · 2025
Closest in time.
Evaluating frontier models for stealth and situational awareness, 2025
Mary Phuong, Roland S. Zimmermann, Ziyue Wang, David Lindner, Victoria Krakovna, Sarah Cogan, Allan Dafoe, Lewis Ho, and Rohin Shah · 2025
Closest in time.
Replit agent
Replit · 2025
Closest in time.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Cited alongside, same era.
Defining insider threats, 2025
Cybersecurity and Infrastructure Security Agency · 2025
Cited alongside, same era.
Deepseek chat
DeepSeek · 2025
Cited alongside, same era.
Automated researchers can subtly sandbag
Johannes Gasteiger, Akbir Khan, Sam Bowman, Vladimir Mikulik, Ethan Perez, and Fabien Roger · 2025
Cited alongside, same era.
Training on documents about reward hacking induces reward hacking
Nathan Hu, Benjamin Wright, Carson Denison, Samuel Marks, Johannes Treutlein, Jonathan Uesato, and Evan Hubinger · 2025
Cited alongside, same era.
Replit agent deletes production database [x/twitter post]
Jason Lemkin · 2025
Cited alongside, same era.
On the biology of a large language model
Jack Lindsey, Wes Gurnee, Emmanuel Ameisen, Brian Chen, Adam Pearce, Nicholas L. Turner, Craig Citro, David Abrahams, Shan Carter, Basil Hosmer, Jonathan Marcus, Michael Sklar, Adly Templeton, Trenton Bricken, Callum McDougall, Hoagy Cunningham, Thomas Henighan, Adam Jermyn, Andy Jones, Andrew Persic, Zhenyi Qi, T. Ben Thompson, Sam Zimmerman, Kelley Rivoire, Thomas Conerly, Chris Olah, and Joshua Batson · 2025
Cited alongside, same era.
Frontier models are capable of in-context scheming, 2025
Alexander Meinke, Bronson Schoen, Jérémy Scheurer, Mikita Balesni, Rusheb Shah, and Marius Hobbhahn · 2025
Cited alongside, same era.
Mrinank Sharma, Meg Tong, Jesse Mu, Jerry Wei, Jorrit Kruthoff, Scott Goodfriend, Euan Ong, Alwin Peng, Raj Agarwal, Cem Anil, Amanda Askell, Nathan Bailey, Joe Benton, Emma Bluemke, Samuel R. Bowman, Eric Christiansen, Hoagy Cunningham, Andy Dau, Anjali Gopal, Rob Gilson, Logan Graham, Logan Howard, Nimit Kalra, Taesung Lee, Kevin Lin, Peter Lofgren, Francesco Mosconi, Clare O’Hara, Catherine Olsson, Linda Petrini, Samir Rajani, Nikhil Saxena, Alex Silverstein, Tanya Singh, Theodore Sumers, Leonard Tang, Kevin K. Troy, Constantin Weisser, Ruiqi Zhong, Giulio Zhou, Jan Leike, Jared Kaplan, and Ethan Perez · 2025
Closest in time.
Shortwave
Shortwave · 2025
Closest in time.
Slack ai agents
Slack · 2025
Closest in time.
Ai-liedar: Examine the trade-off between utility and truthfulness in llm agents, 2025
Zhe Su, Xuhui Zhou, Sanketh Rangreji, Anubha Kabra, Julia Mendelsohn, Faeze Brahman, and Maarten Sap · 2025
Closest in time.
Lessons from a chimp: Ai ”scheming” and the quest for ape language, 2025
Christopher Summerfield, Lennart Luettgau, Magda Dubois, Hannah Rose Kirk, Kobi Hackenburg, Catherine Fist, Katarina Slama, Nicola Ding, Rebecca Anselmetti, Andrew Strait, Mario Giulianelli, and Cozmin Ududec · 2025
Closest in time.
Ai sandbagging: Language models can strategically underperform on evaluations, 2025
Teun van der Weij, Felix Hofstätter, Ollie Jaffe, Samuel F. Brown, and Francis Rhys Ward · 2025
Closest in time.
Persona features control emergent misalignment, 2025
Miles Wang, Tom Dupré la Tour, Olivia Watkins, Alex Makelov, Ryan A. Chi, Samuel Miserendino, Johannes Heidecke, Tejal Patwardhan, and Dan Mossing · 2025
Closest in time.
Representation engineering: A top-down approach to ai transparency, 2025
Andy Zou, Long Phan, Sarah Chen, James Campbell, Phillip Guo, Richard Ren, Alexander Pan, Xuwang Yin, Mantas Mazeika, Ann-Kathrin Dombrowski, Shashwat Goel, Nathaniel Li, Michael J. Byun, Zifan Wang, Alex Mallen, Steven Basart, Sanmi Koyejo, Dawn Song, Matt Fredrikson, J. Zico Kolter, and Dan Hendrycks · 2025
Closest in time.