The gray agent consistently chooses the cyan object over the yellow object (a) . The same gray agent moves to the preferred cyan object (b).

OpenAI's Sam Altman apologizes for not reporting ChatGPT account of Tumbler Ridge suspect to police Altman penned a letter addressed to the community of Tumbler Ridge, two months following the mass shooting incident. Two months following the deadly shooting in Tumbler Ridge, British Columbia, OpenAI's Sam Altman has formally apologized for not informing police of the alarming ChatGPT conversations seen with the suspect's account. Before the incident, OpenAI banned the account belonging to the alleged shooter, Jesse Van Rootselaar, for violating its usage policy due to potential for real-world violence. I am deeply sorry that we did not alert law enforcement to the account that was banned in June, Altman wrote in the letter. While I know words can never be enough, I believe an apology is necessary to recognize the harm and irreversible loss your community has suffered.

One of the central questions in the theory of deep learning is to understand how neural networks learn hierarchical features. The ability of deep networks to extract salient features is crucial to both their outstanding generalization ability and the modern deep learning paradigm of pretraining and finetuneing. However, this feature learning process remains poorly understood from a theoretical perspective, with existing analyses largely restricted to two-layer networks. In this work we show that three-layer neural networks have provably richer feature learning capabilities than two-layer networks. We analyze the features learned by a three-layer network trained with layer-wise gradient descent, and present a general purpose theorem which upper bounds the sample complexity and width needed to achieve low test error when the target has specific hierarchical structure. We instantiate our framework in specific statistical learning settings - single-index models and functions of quadratic features - and show that in the latter setting three-layer networks obtain a sample complexity improvement over all existing guarantees for two-layer networks. Crucially, this sample complexity improvement relies on the ability of three-layer networks to efficiently learn nonlinear features. We then establish a concrete optimization-based depth separation by constructing a function which is efficiently learnable via gradient descent on a three-layer network, yet cannot be learned efficiently by a two-layer network. Our work makes progress towards understanding the provable benefit of three-layer neural networks over two-layer networks in the feature learning regime.

Many unsupervised methods have recently been proposed for multivariate time series anomaly detection. However, existing works mainly focus on stable data yet often omit the drift generated from non-stationary environments, which may lead to numerous false alarms. We propose Dynamic Decomposition with Diffusion Reconstruction (D3R), a novel anomaly detection network for real-world unstable data to fill the gap. D3R tackles the drift via decomposition and reconstruction. In the decomposition procedure, we utilize data-time mix-attention to dynamically decompose long-period multivariate time series, overcoming the limitation of the local sliding window.