6 papers
More Capable, Less Cooperative? When LLMs Fail At Zero-Cost Collaboration
Advait Yadav, Sid Black, Oliver Sourbut
Large language model (LLM) agents increasingly coordinate in multi-agent systems, yet we lack an understanding of where and why cooperation fails. Many real-world coordination prob…
Prioritization of Risks from Artificial Intelligence: A Delphi Study of 272 International Experts
Alexander K. Saeri, Jess Graham, Michael Noetel +185
Artificial intelligence poses many risks, ranging from familiar present-day harms to unprecedented and potentially catastrophic ones. Effective risk management requires prioritizat…
Do Large Language Models Know What They Are Capable Of?
Casey O. Barkan, Sid Black, Oliver Sourbut
We investigate whether large language models (LLMs) can predict whether they will succeed on a given task and whether their predictions improve as they progress through multi-step…
RepliBench: Evaluating the Autonomous Replication Capabilities of Language Model Agents
Sid Black, Asa Cooper Stickland, Jake Pencharz +7
Uncontrollable autonomous replication of language model agents poses a critical safety risk. To better understand this risk, we introduce RepliBench, a suite of evaluations designe…
Foundational Challenges in Assuring Alignment and Safety of Large Language Models
Usman Anwar, Abulhair Saparov, Javier Rando +39
This work identifies 18 foundational challenges in assuring the alignment and safety of large language models (LLMs). These challenges are organized into three different categories…
Cooperation and Control in Delegation Games
Oliver Sourbut, Lewis Hammond, Harriet Wood
Many settings of interest involving humans and machines -- from virtual personal assistants to autonomous vehicles -- can naturally be modelled as principals (humans) delegating to…