Related papers: The Hot Mess of AI: How Does Misalignment Scale Wi…
AI models that predict the future behavior of a system (a.k.a. predictive AI models) are central to intelligent decision-making. However, decision-making using predictive AI models often results in suboptimal performance. This is primarily…
We study \emph{Human Projection} (HP): people's tendency to evaluate AI using the same frameworks they use for humans -- treating features such as task difficulty and the reasonableness of mistakes as diagnostic of overall ability. We…
Artificial intelligence (AI) systems attempt to imitate human behavior. How well they do this imitation is often used to assess their utility and to attribute human-like (or artificial) intelligence to them. However, most work on AI refers…
Although AI has become increasingly smart, its wisdom has not kept pace. In this article, we examine what is known about human wisdom and sketch a vision of its AI counterpart. We analyze human wisdom as a set of strategies for solving…
. It is typically assumed that for the successful use of machine learning algorithms, these algorithms should have a higher accuracy than a human expert. Moreover, if the average accuracy of ML algorithms is lower than that of a human…
As AI technologies increase in capability and ubiquity, AI accidents are becoming more common. Based on normal accident theory, high reliability theory, and open systems theory, we create a framework for understanding the risks associated…
AI alignment research aims to develop techniques to ensure that AI systems do not cause harm. However, every alignment technique has failure modes, which are conditions in which there is a non-negligible chance that the technique fails to…
Assured AI in unrestricted settings is a critical problem. Our framework addresses AI assurance challenges lying at the intersection of domain adaptation, fairness, and counterfactuals analysis, operating via the discovery and intervention…
The understanding of bias in AI is currently undergoing a revolution. Initially understood as errors or flaws, biases are increasingly recognized as integral to AI systems and sometimes preferable to less biased alternatives. In this paper,…
AI systems are often used to make or contribute to important decisions in a growing range of applications, including criminal justice, hiring, and medicine. Since these decisions impact human lives, it is important that the AI systems act…
We have witnessed superhuman intelligence thanks to the fast development of large language models and multimodal language models. As the application of such superhuman models becomes more and more popular, a critical question arises here:…
A significant element of human cooperative intelligence lies in our ability to identify opportunities for fruitful collaboration; and conversely to recognise when the task at hand is better pursued alone. Research on flexible cooperation in…
As autonomous AI agents are increasingly deployed in high-stakes environments, ensuring their safety and alignment with human values is becoming a practical deployment concern. Current benchmarks for AI agents primarily evaluate refusal of…
In decision making tasks under uncertainty, humans display characteristic biases in seeking, integrating, and acting upon information relevant to the task. Here, we reexamine data from previous carefully designed experiments, collected at…
Highly capable AI systems could secretly pursue misaligned goals -- what we call "scheming". Because a scheming AI would deliberately try to hide its misaligned goals and actions, measuring and mitigating scheming requires different…
Active automata learning (AAL) algorithms can learn a behavioral model of a system from interacting with it. The primary challenge remains scaling to larger models, in particular in the presence of many possible inputs to the system. Modern…
Models trained on different datasets can be merged by a weighted-averaging of their parameters, but why does it work and when can it fail? Here, we connect the inaccuracy of weighted-averaging to mismatches in the gradients and propose a…
Recent human-computer interaction (HCI) research has revealed a widespread misalignment between how developers design workplace artificial intelligence (AI) systems, and what workers actually need from them. Yet, little research has…
Recent work has advocated for training AI models on ever-larger datasets, arguing that as the size of a dataset increases, the performance of a model trained on that dataset will correspondingly increase (referred to as "scaling laws"). In…
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, we present evidence for the claim that LMs may show inverse…