Across the world, hundreds of people have come to believe they have made extraordinary scientific discoveries with AI chatbots such as ChatGPT, Claude and Gemini. Others say their AI has'awakened', or is leading them to a higher spiritual realm. The Guardian journalist Michael Safi begins investigating a phenomenon labelled'AI psychosis', travelling to the US to meet two people who have been on weird journeys with their chatbots

People are becoming convinced AI chatbots have helped them make scientific breakthroughs, cure diseases or invent new technologies. What does this reveal about a technology used by more than a billion people?

On Rashomon sets, the mathematics of simplicity, and why we don't need black boxes: an interview with Cynthia Rudin Welcome back to AI Pioneers - in-depth conversations with those shaping the field . This time, we speak with Cynthia Rudin, a trailblazer in the field of interpretable machine learning. Winner of the 2022 Squirrel AI Award for Artificial Intelligence for the Benefit of Humanity, Cynthia's algorithms are already predicting seizures, aiding crime detection, and powering biological research . We discuss black boxes, Rashomon sets, and what's next for her lab - from cancer detection to interpretable AI-generated music. Can you tell me a bit about your background - what drew you into the field of interpretable machine learning?

Neural networks are often described as black boxes, reflecting the significant challenge of understanding their internal workings and interactions. We propose a different perspective that challenges the prevailing view: rather than being inscrutable, neural networks exhibit patterns in their raw population activity that mirror regularities in the training data. We refer to this as the \textit{Reflection Hypothesis} and provide evidence for this phenomenon in both simple recurrent neural networks (RNNs) and complex large language models (LLMs). Building on this insight, we propose to leverage cognitively-inspired methods of \textit{chunking} to segment high-dimensional neural population dynamics into interpretable units that reflect underlying concepts. We propose three methods to extract these emerging entities, complementing each other based on label availability and neural data dimensionality.

Recently, interpretable machine learning has re-explored concept bottleneck models (CBM). An advantage of this model class is the user's ability to intervene on predicted concept values, affecting the downstream output. In this work, we introduce a method to perform such concept-based interventions on neural networks, which are not interpretable by design, only given a small validation set with concept labels. Furthermore, we formalise the notion of as a measure of the effectiveness of concept-based interventions and leverage this definition to fine-tune black boxes. Empirically, we explore the intervenability of black-box classifiers on synthetic tabular and natural image benchmarks. We focus on backbone architectures of varying complexity, from simple, fully connected neural nets to Stable Diffusion. We demonstrate that the proposed fine-tuning improves intervention effectiveness and often yields better-calibrated predictions. To showcase the practical utility of our techniques, we apply them to deep chest X-ray classifiers and show that fine-tuned black boxes are more intervenable than CBMs. Lastly, we establish that our methods are still effective under vision-language-model-based concept annotations, alleviating the need for a human-annotated validation set.

Four new books grapple with a global mental-health crisis and the dawn of algorithmic therapy. A technician adjusts the wiring inside the Mark I Perceptron. This early AI system was designed not by a mathematician but by a psychologist. More than a billion people worldwide suffer from a mental-health condition, according to the World Health Organization. The prevalence of anxiety and depression is growing in many demographics, particularly young people, and suicide is claiming hundreds of thousands of lives globally each year. Given the clear demand for accessible and affordable mental-health services, it's no wonder that people have looked to artificial intelligence for possible relief.

There have been multiple works that try to ascertain explanations for decisions of black box models on particular inputs by perturbing the input or by sampling around it, creating a neighborhood and then fitting a sparse (linear) model (e.g.