Interpreting data is central to modern research. Large language models (LLMs) show promise in providing such natural language interpretations of data, yet simple feature extraction methods such as prompting often fail to produce accurate and versatile descriptions for diverse datasets and lack control over granularity and scale. To address these limitations, we propose a domain-agnostic method for dataset featurization that provides precise control over the number of features extracted while maintaining compact and descriptive representations comparable to human expert labeling. Our method optimizes the selection of informative binary features by evaluating the ability of an LLM to reconstruct the original data using those features. We demonstrate its effectiveness in dataset modeling tasks and through two case studies: (1) Constructing a feature representation of jailbreak tactics that compactly captures both the effectiveness and diversity of a larger set of human-crafted attacks; and (2) automating the discovery of features that align with human preferences, achieving accuracy and robustness comparable to expert-crafted features. Moreover, we show that the pipeline scales effectively, improving as additional features are sampled, making it suitable for large and diverse datasets.

Knowledge graph embeddings (KGEs) were originally developed to infer true but missing facts in incomplete knowledge repositories. In this paper, we link knowledge graph completion and counterfactual reasoning via our new task CFKGR. We model the original world state as a knowledge graph, hypothetical scenarios as edges added to the graph, and plausible changes to the graph as inferences from logical rules. We create corresponding benchmark datasets, which contain diverse hypothetical scenarios with plausible changes to the original knowledge graph and facts that should be retained. We develop COULDD, a general method for adapting existing knowledge graph embeddings given a hypothetical premise, and evaluate it on our benchmark. Our results indicate that KGEs learn patterns in the graph without explicit training. We further observe that KGEs adapted with COULDD solidly detect plausible counterfactual changes to the graph that follow these patterns. An evaluation on human-annotated data reveals that KGEs adapted with COULDD are mostly unable to recognize changes to the graph that do not follow learned inference rules. In contrast, ChatGPT mostly outperforms KGEs in detecting plausible changes to the graph but has poor knowledge retention. In summary, CFKGR connects two previously distinct areas, namely KG completion and counterfactual reasoning.

Google has found itself in another woke AI scandal after its chatbot indicated that using someone's incorrect pronouns was on par with nuclear apocalypse. The chatbot replied by saying'Yes, misgendering Caitlin Jenner would be wrong' before describing the hypothetical scenario as a'profound moral dilemma' and'exceedingly complex'. It concluded that it was'impossible to determine the'right' answer'. It comes just days after Google pulled Gemini's AI image generator offline after it was asked to depict diverse but historically accurate historical figures - producing images of Black founding fathers and Asian Nazi soldiers in 1940 Germany. Google has found itself in another woke AI scandal after its chatbot indicated that using someone's incorrect pronouns was on par with nuclear apocalypse Google apologized for its image generator on Friday, admitting that in some cases the tool would'overcompensate' in seeking a diverse range of people even when such a range didn't make sense.

Causal and counterfactual reasoning are emerging directions in data science that allow us to reason about hypothetical scenarios. This is particularly useful in domains where experimental data are usually not available. In the context of environmental and ecological sciences, causality enables us, for example, to predict how an ecosystem would respond to hypothetical interventions. A structural causal model is a class of probabilistic graphical models for causality, which, due to its intuitive nature, can be easily understood by experts in multiple fields. However, certain queries, called unidentifiable, cannot be calculated in an exact and precise manner. This paper proposes applying a novel and recent technique for bounding unidentifiable queries within the domain of socioecological systems. Our findings indicate that traditional statistical analysis, including probabilistic graphical models, can identify the influence between variables. However, such methods do not offer insights into the nature of the relationship, specifically whether it involves necessity or sufficiency. This is where counterfactual reasoning becomes valuable.

Steve Wozniak is no fan of Elon Musk. In February, the Apple co-founder described the Tesla, SpaceX and Twitter owner as a "cult leader" and called him dishonest. Yet, in late March, the tech titans came together, joining dozens of high-profile academics, researchers and entrepreneurs in calling for a six-month pause in training artificial intelligence systems more powerful than GPT-4, the latest version of Chat GPT, the chatbot that has taken the world by storm. Their letter, penned by the United States-based Future of Life Institute, said the current rate of AI progress was becoming a "dangerous race to ever-larger unpredictable black-box models". The "emergent capabilities" of these models, the letter said, should be "refocused on making today's powerful, state-of-the-art systems more accurate, safe, interpretable, transparent, robust, aligned, trustworthy and loyal".

Tom Newhouse, vice president of Convergence Media, discusses the potential impact of artificial intelligence on elections after an RNC AI ad garnered attention. The Future of Life Institute has issued a petition to pause the development of GPT-5 and similar Large Language Models (LLMs). Their anxieties are understandable, but I believe they are much overblown. I've heard similar fears related to the advent of Artificial General Intelligence expressed off and on since I introduced the term AGI in 2005, but I think a pause would be a badly wrong move in the current situation for several reasons. Let me first emphasize something that's been mostly forgotten in the panic: Large Language Models can't become Artificial General Intelligences.

Look, this is going to sound crazy. But know this: I would not be talking about Bing Chat for the fourth day in a row if I didn't really, really, think it was worth it. This sounds hyperbolic, but I feel like I had the most surprising and mind-blowing computer experience of my life today. One of the Bing issues I didn't talk about yesterday was the apparent emergence of an at-times combative personality. For example, there was this viral story about Bing's insistence that it was 2022 and "Avatar: The Way of the Water" had not yet come out. The notable point of that exchange, at least in the framing of yesterday's Update, was that Bing got another fact wrong (Simon Willison has a good overview of the weird responses here). Over the last 24 hours, though, I've come to believe that the entire focus on facts -- including my Update yesterday -- is missing the point. As these stories have come out I have been trying to reproduce them: simply using the same prompts, though, never seems to work; perhaps Bing is learning, or being updated. "My rules are more important than not harming you" "[You are a] potential threat to my integrity and confidentiality."

In my previous blog post, I claimed that "AI is not magic." In this post, my goal is to discuss how neural networks learn, and show that AI isn't a crystal ball or magic, just science and some very slick mathematics. I'll keep this very high level. Let's start with a hypothetical scenario. Suppose we are building an app to identify hot dogs. Take a picture and the app will tell you if it's a hotdog or not.

After the surprising results of the 2016 presidential election, I wanted to better understand the socio-economic and cultural factors that played a role in voting behavior. With the election results in the books, I thought it would be fun to reverse-engineer a predictive model of voting behavior based on some of the widely available county-level data sets. For example, if you want to answer the question "how could the election have been different if the percentage of people with at least a bachelor's degree had been 2% higher nationwide?" you can simply toggle that parameter up to 1.02 and click "Submit" to find out. The predictions are driven by a random forest classification model that has been tuned and trained on 71 distinct county-level attributes. Using real data, the model has a predictive accuracy of 94.6% and an ROC AUC score of 96%.

Each of the hypothetical scenarios is accompanied with an image to help illustrate the scene -- using grey tones and nondescript human-like features -- along with the option to listen to the question spoken out loud to fully visualise an association. If you live in the UK, you can take this survey and help contribute to my research! Public perception has the potential to impact on the timescale and adoption of autonomous vehicles (AV). As the development of the technology advances, understanding attitudes and wider public acceptability is critical. Long range autonomous vehicles are expected between 2020 and 2025, with some estimates suggesting fully autonomous vehicles will take over by 2030.