7 accepted papers
Despite rapid progress on AI benchmarks, the real-world meaning of benchmark performance remains unclear. To quantify the capabilities of AI systems in terms of human capabilities, we propose a new metric: 50%-task-completion time horizon. This is the time humans typically take to complete tasks tha…
Frontier AI safety policies highlight automation of AI research and development (R&D) by AI agents as an important capability to anticipate. However, there exist few evaluations for AI R&D capabilities, and none that are highly realistic and have a direct comparison to human performance. We introduc…
We propose using mechanistic interpretability -- techniques for reverse engineering model weights into human-interpretable algorithms -- to derive and compactly prove formal guarantees on model performance. We prototype this approach by formally proving accuracy lower bounds for a small transformer…
AI systems based on deep learning have reached or surpassed human performance in a range of narrow domains. In coming years or decades, artificial general intelligence (AGI) may surpass human capabilities at many critical tasks. In this position paper, we examine the technical difficulty of fine-tun…
Universality is a key hypothesis in mechanistic interpretability -- that different models learn similar features and circuits when trained on similar tasks. In this work, we study the universality hypothesis by examining how small networks learn to implement group compositions. We present a novel al…
Neural networks often exhibit emergent behavior in which qualitatively new capabilities that arise from scaling up the number of parameters, training data, or even the number of steps. One approach to understanding emergence is to find the continuous \textit{progress measures} that underlie the seem…
In the future, powerful AI systems may be deployed in high-stakes settings, where a single failure could be catastrophic. One technique for improving AI safety in high-stakes settings is adversarial training, which uses an adversary to generate examples to train on in order to achieve better worst-c…