1 code implementation • 10 Jan 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, Ethan Perez
We find that such backdoor behavior can be made persistent, so that it is not removed by standard safety training techniques, including supervised fine-tuning, reinforcement learning, and adversarial training (eliciting unsafe behavior and then training to remove it).
no code implementations • 26 Oct 2023 • Yoshua Bengio, Geoffrey Hinton, Andrew Yao, Dawn Song, Pieter Abbeel, Yuval Noah Harari, Ya-Qin Zhang, Lan Xue, Shai Shalev-Shwartz, Gillian Hadfield, Jeff Clune, Tegan Maharaj, Frank Hutter, Atılım Güneş Baydin, Sheila Mcilraith, Qiqi Gao, Ashwin Acharya, David Krueger, Anca Dragan, Philip Torr, Stuart Russell, Daniel Kahneman, Jan Brauner, Sören Mindermann
In this short consensus paper, we outline risks from upcoming, advanced AI systems.
no code implementations • 20 Oct 2023 • Sandipan Kundu, Yuntao Bai, Saurav Kadavath, Amanda Askell, Andrew Callahan, Anna Chen, Anna Goldie, Avital Balwit, Azalia Mirhoseini, Brayden McLean, Catherine Olsson, Cassie Evraets, Eli Tran-Johnson, Esin Durmus, Ethan Perez, Jackson Kernion, Jamie Kerr, Kamal Ndousse, Karina Nguyen, Nelson Elhage, Newton Cheng, Nicholas Schiefer, Nova DasSarma, Oliver Rausch, Robin Larson, Shannon Yang, Shauna Kravec, Timothy Telleen-Lawton, Thomas I. Liao, Tom Henighan, Tristan Hume, Zac Hatfield-Dodds, Sören Mindermann, Nicholas Joseph, Sam McCandlish, Jared Kaplan
Constitutional AI offers an alternative, replacing human feedback with feedback from AI models conditioned only on a list of written principles.
1 code implementation • 26 Sep 2023 • Lorenzo Pacchiardi, Alex J. Chan, Sören Mindermann, Ilan Moscovitz, Alexa Y. Pan, Yarin Gal, Owain Evans, Jan Brauner
Large language models (LLMs) can "lie", which we define as outputting false statements despite "knowing" the truth in a demonstrable sense.
no code implementations • 30 Aug 2022 • Richard Ngo, Lawrence Chan, Sören Mindermann
In coming years or decades, artificial general intelligence (AGI) may surpass human capabilities at many critical tasks.
1 code implementation • 14 Jun 2022 • Sören Mindermann, Jan Brauner, Muhammed Razzak, Mrinank Sharma, Andreas Kirsch, Winnie Xu, Benedikt Höltgen, Aidan N. Gomez, Adrien Morisot, Sebastian Farquhar, Yarin Gal
But most computation and time is wasted on redundant and noisy points that are already learnt or not learnable.
no code implementations • 6 Jul 2021 • Sören Mindermann, Muhammed Razzak, Winnie Xu, Andreas Kirsch, Mrinank Sharma, Adrien Morisot, Aidan N. Gomez, Sebastian Farquhar, Jan Brauner, Yarin Gal
We introduce Goldilocks Selection, a technique for faster model training which selects a sequence of training points that are "just right".
1 code implementation • 8 Mar 2021 • Andrew Jesson, Sören Mindermann, Yarin Gal, Uri Shalit
We study the problem of learning conditional average treatment effects (CATE) from high-dimensional, observational data with unobserved confounders.
no code implementations • NeurIPS 2020 • Mrinank Sharma, Sören Mindermann, Jan Markus Brauner, Gavin Leech, Anna B. Stephenson, Tomáš Gavenčiak, Jan Kulveit, Yee Whye Teh, Leonid Chindelevitch, Yarin Gal
To what extent are effectiveness estimates of nonpharmaceutical interventions (NPIs) against COVID-19 influenced by the assumptions our models make?
1 code implementation • NeurIPS 2020 • Andrew Jesson, Sören Mindermann, Uri Shalit, Yarin Gal
We show that our methods enable us to deal gracefully with situations of "no-overlap", common in high-dimensional data, where standard applications of causal effect approaches fail.
1 code implementation • 9 Sep 2018 • Sören Mindermann, Rohin Shah, Adam Gleave, Dylan Hadfield-Menell
We propose structuring this process as a series of queries asking the user to compare between different reward functions.
no code implementations • NeurIPS 2018 • Stuart Armstrong, Sören Mindermann
Inverse reinforcement learning (IRL) attempts to infer human rewards or preferences from observed behavior.