English
Related papers

Related papers: Frontier Models Can Take Actions at Low Probabilit…

200 papers

Sufficiently capable models could subvert human oversight and decision-making in important contexts. For example, in the context of AI development, models could covertly sabotage efforts to evaluate their own dangerous capabilities, to…

If AI models can detect when they are being evaluated, the effectiveness of evaluations might be compromised. For example, models could have systematically different behavior during evaluations, leading to less reliable benchmarks for…

Computation and Language · Computer Science 2025-07-17 Joe Needham , Giles Edkins , Govind Pimpale , Henning Bartsch , Marius Hobbhahn

A comprehensive approach to addressing catastrophic risks from AI models should cover the full model lifecycle. This paper explores contingency plans for cases where pre-deployment risk management falls short: where either very dangerous…

Computers and Society · Computer Science 2023-10-03 Joe O'Brien , Shaun Ee , Zoe Williams

Recent work has demonstrated the plausibility of frontier AI models scheming -- knowingly and covertly pursuing an objective misaligned with its developer's intentions. Such behavior could be very hard to detect, and if present in future…

Machine Learning · Computer Science 2025-07-04 Mary Phuong , Roland S. Zimmermann , Ziyue Wang , David Lindner , Victoria Krakovna , Sarah Cogan , Allan Dafoe , Lewis Ho , Rohin Shah

Assessing the capabilities and risks of frontier AI systems is a critical area of research, and recent work has shown that repeated sampling from models can dramatically increase both. For instance, repeated sampling has been shown to…

Artificial Intelligence · Computer Science 2025-10-08 Joshua Kazdan , Rylan Schaeffer , Youssef Allouah , Colin Sullivan , Kyssen Yu , Noam Levi , Sanmi Koyejo

Predicting changes from scaling advanced AI systems is a desirable property for engineers, economists, governments and industry alike, and, while a well-established literature exists on how pretraining performance scales, predictable…

The recent explosion in the capabilities of large language models has led to a wave of interest in how best to prompt a model to perform a given task. While it may be tempting to simply choose a prompt based on average performance on a…

Machine Learning · Computer Science 2024-03-29 Thomas P. Zollo , Todd Morrill , Zhun Deng , Jake C. Snell , Toniann Pitassi , Richard Zemel

Observability into the decision making of modern AI systems may be required to safely deploy increasingly capable agents. Monitoring the chain-of-thought (CoT) of today's reasoning models has proven effective for detecting misbehavior.…

As coding agents gain access to shells, repositories, and user files, least-privilege authorization becomes a prerequisite for safe deployment: an agent should receive enough authority to complete the task, without unnecessary authority…

Cryptography and Security · Computer Science 2026-05-18 Zheng Yan , Jingxiang Weng , Charles Chen , Dengyun Peng , Ethan Qin , Jiannan Guan , Jinhao Liu , Qiming Yu , Yixin Yuan , Fanqing Meng , Carl Che , Mengkang Hu

GPT-3 can perform numerous tasks when provided a natural language prompt that contains a few training examples. We show that this type of few-shot learning can be unstable: the choice of prompt format, training examples, and even the order…

Computation and Language · Computer Science 2021-06-14 Tony Z. Zhao , Eric Wallace , Shi Feng , Dan Klein , Sameer Singh

It has been experimentally observed in recent years that multi-layer artificial neural networks have a surprising ability to generalize, even when trained with far more parameters than observations. Is there a theoretical basis for this?…

Machine Learning · Statistics 2018-09-19 Andrew R. Barron , Jason M. Klusowski

Developers try to evaluate whether an AI system can be misused by adversaries before releasing it; for example, they might test whether a model enables cyberoffense, user manipulation, or bioterrorism. In this work, we show that…

Cryptography and Security · Computer Science 2024-07-03 Erik Jones , Anca Dragan , Jacob Steinhardt

Mitigating reward hacking--where AI systems misbehave due to flaws or misspecifications in their learning objectives--remains a key challenge in constructing capable and aligned models. We show that we can monitor a frontier reasoning…

Artificial Intelligence · Computer Science 2025-03-18 Bowen Baker , Joost Huizinga , Leo Gao , Zehao Dou , Melody Y. Guan , Aleksander Madry , Wojciech Zaremba , Jakub Pachocki , David Farhi

Machine learning applications frequently come with multiple diverse objectives and constraints that can change over time. Accordingly, trained models can be tuned with sets of hyper-parameters that affect their predictive behavior (e.g.,…

Machine Learning · Computer Science 2022-10-17 Bracha Laufer-Goldshtein , Adam Fisch , Regina Barzilay , Tommi Jaakkola

LLMs demonstrate remarkable reasoning capabilities, yet whether they utilize internal world models or rely on sophisticated pattern matching remains open. We study LLMs through the lens of robustness of their code understanding using a…

Software Engineering · Computer Science 2026-04-21 Claudio Spiess , Prem Devanbu , Earl T. Barr

Current regulations on powerful AI capabilities are narrowly focused on "foundation" or "frontier" models. However, these terms are vague and inconsistently defined, leading to an unstable foundation for governance efforts. Critically,…

Computers and Society · Computer Science 2024-09-27 Ritwik Gupta , Leah Walker , Rodolfo Corona , Stephanie Fu , Suzanne Petryk , Janet Napolitano , Trevor Darrell , Andrew W. Reddie

Code language models are increasingly adopted for both understanding and generative tasks. Despite their success, these models frequently produce overconfident incorrect predictions and underconfident correct predictions, undermining their…

Software Engineering · Computer Science 2026-05-20 Ravishka Rathnasuriya , Wei Yang

Excessively changing policies in many real world scenarios is difficult, unethical, or expensive. After all, doctor guidelines, tax codes, and price lists can only be reprinted so often. We may thus want to only change a policy when it is…

Machine Learning · Statistics 2019-10-16 Benjamin Lansdell , Sofia Triantafillou , Konrad Kording

In a well-calibrated risk prediction model, the average predicted probability is close to the true event rate for any given subgroup. Such models are reliable across heterogeneous populations and satisfy strong notions of algorithmic…

Machine Learning · Computer Science 2023-07-31 Jean Feng , Alexej Gossmann , Romain Pirracchio , Nicholas Petrick , Gene Pennello , Berkman Sahiner

Today's leading AI models engage in sophisticated behaviour when placed in strategic competition. They spontaneously attempt deception, signaling intentions they do not intend to follow; they demonstrate rich theory of mind, reasoning about…

Artificial Intelligence · Computer Science 2026-02-17 Kenneth Payne
‹ Prev 1 2 3 10 Next ›