24 citations · 43 across the 5 of their papers we have counts for
5 papers
Multi-Agent Risks from Advanced AI
Lewis Hammond, Alan Chan, Jesse Clifton +41
The rapid development of advanced AI agents and the imminent deployment of many instances of these agents will give rise to multi-agent systems of unprecedented complexity. These s…
Can Go AIs be adversarially robust?
Tom Tseng, Euan McLean, Kellin Pelrine +2
Prior work found that superhuman Go AIs can be defeated by simple adversarial strategies, especially "cyclic" attacks. In this paper, we study whether adding natural countermeasure…
Exploiting Novel GPT-4 APIs
Kellin Pelrine, Mohammad Taufeeque, Michał Zając +2
Language model attacks typically assume one of two extreme threat models: full white-box access to model weights, or black-box access limited to a text generation API. However, rea…
Inverse Scaling: When Bigger Isn't Better
Ian R. McKenzie, Alexander Lyzhov, Michael Pieler +24
Work on scaling laws has found that large language models (LMs) show predictable improvements to overall loss with increased scale (model size, training data, and compute). Here, w…
Language models are better than humans at next-token prediction
Buck Shlegeris, Fabien Roger, Lawrence Chan +1
Current language models are considered to have sub-human capabilities at natural language tasks like question-answering or writing code. However, language models are not trained to…