Information removal or suppression in large language models (LLMs) is a desired functionality, useful in AI regulation, legal compliance, safety, and privacy. LLM unlearning methods aim to remove information on demand from LLMs. Current LLM unlearning methods struggle to balance the unlearning efficacy and utility due to the competing nature of these objectives. Keeping the unlearning process computationally feasible without assuming access to the model weights is an overlooked area. We present the first agentic LLM unlearning (ALU) method, a multi-agent, retrain-free, model-agnostic approach to LLM unlearning that achieves effective unlearning while preserving the utility. Our ALU framework unlearns by involving multiple LLM agents, each designed for a specific step in the unlearning process, without the need to update model weights for any of the agents in the framework. Users can easily request any set of unlearning instances in any sequence, and ALU seamlessly adapts in real time. This is facilitated without requiring any changes in the underlying LLM model. Through extensive experiments on established benchmarks (TOFU, WMDP, WPU) and jailbreaking techniques (many shot, target masking, other languages), we demonstrate that ALU consistently stands out as the most robust LLM unlearning framework among current state-of-the-art methods while incurring a low constant-time cost. We further highlight ALU's superior performance compared to existing methods when evaluated at scale. Specifically, ALU is assessed on up to 1000 unlearning targets, exceeding the evaluation scope of all previously proposed LLM unlearning methods.

Recent work showed Best-of-N (BoN) jailbreaking using repeated use of random augmentations (such as capitalization, punctuation, etc) is effective against all major large language models (LLMs). We have found that $100\%$ of the BoN paper's successful jailbreaks (confidence interval $[99.65\%, 100.00\%]$) and $99.8\%$ of successful jailbreaks in our replication (confidence interval $[99.28\%, 99.98\%]$) were blocked with our Defense Against The Dark Prompts (DATDP) method. The DATDP algorithm works by repeatedly utilizing an evaluation LLM to evaluate a prompt for dangerous or manipulative behaviors--unlike some other approaches, DATDP also explicitly looks for jailbreaking attempts--until a robust safety rating is generated. This success persisted even when utilizing smaller LLMs to power the evaluation (Claude and LLaMa-3-8B-instruct proved almost equally capable). These results show that, though language models are sensitive to seemingly innocuous changes to inputs, they seem also capable of successfully evaluating the dangers of these inputs. Versions of DATDP can therefore be added cheaply to generative AI systems to produce an immediate significant increase in safety.

Augmented Reality (AR) enhances the real world by integrating virtual content, yet ensuring the quality, usability, and safety of AR experiences presents significant challenges. Could Vision-Language Models (VLMs) offer a solution for the automated evaluation of AR-generated scenes? Could Vision-Language Models (VLMs) offer a solution for the automated evaluation of AR-generated scenes? In this study, we evaluate the capabilities of three state-of-the-art commercial VLMs -- GPT, Gemini, and Claude -- in identifying and describing AR scenes. For this purpose, we use DiverseAR, the first AR dataset specifically designed to assess VLMs' ability to analyze virtual content across a wide range of AR scene complexities. Our findings demonstrate that VLMs are generally capable of perceiving and describing AR scenes, achieving a True Positive Rate (TPR) of up to 93% for perception and 71% for description. While they excel at identifying obvious virtual objects, such as a glowing apple, they struggle when faced with seamlessly integrated content, such as a virtual pot with realistic shadows. Our results highlight both the strengths and the limitations of VLMs in understanding AR scenarios. We identify key factors affecting VLM performance, including virtual content placement, rendering quality, and physical plausibility. This study underscores the potential of VLMs as tools for evaluating the quality of AR experiences.

Large language models (LLMs) have achieved remarkable performance on various natural language tasks. However, they are trained on static corpora and their knowledge can become outdated quickly in the fast-changing world. This motivates the development of knowledge editing (KE) to update specific knowledge in LLMs without changing unrelated others or compromising their pre-trained capabilities. Previous efforts sought to update a small amount of parameters of a LLM and proved effective for making selective updates. Nonetheless, the edited LLM often exhibits degraded ability to reason about the new knowledge. In this work, we identify a key issue: heterogeneous token overfitting (HTO), where the LLM overfits different tokens in the provided knowledge at varying rates. To tackle this, we propose OVERTONE, a token-level smoothing method that mitigates HTO by adaptively refining the target distribution. Theoretically, OVERTONE offers better parameter updates with negligible computation overhead. It also induces an implicit DPO but does not require preference data pairs. Extensive experiments across four editing methods, two LLMs, and diverse scenarios demonstrate the effectiveness and versatility of our method.

MarketSenseAI is a novel framework for holistic stock analysis which leverages Large Language Models (LLMs) to process financial news, historical prices, company fundamentals and the macroeconomic environment to support decision making in stock analysis and selection. In this paper, we present the latest advancements on MarketSenseAI, driven by rapid technological expansion in LLMs. Through a novel architecture combining Retrieval-Augmented Generation and LLM agents, the framework processes SEC filings and earnings calls, while enriching macroeconomic analysis through systematic processing of diverse institutional reports. We demonstrate a significant improvement in fundamental analysis accuracy over the previous version. Empirical evaluation on S\&P 100 stocks over two years (2023-2024) shows MarketSenseAI achieving cumulative returns of 125.9% compared to the index return of 73.5%, while maintaining comparable risk profiles. Further validation on S\&P 500 stocks during 2024 demonstrates the framework's scalability, delivering a 33.8% higher Sortino ratio than the market. This work marks a significant advancement in applying LLM technology to financial analysis, offering insights into the robustness of LLM-driven investment strategies.

Generative AI enables automated, effective manipulation at scale. Despite the growing general ethical discussion around generative AI, the specific manipulation risks remain inadequately investigated. This article outlines essential inquiries encompassing conceptual, empirical, and design dimensions of manipulation, pivotal for comprehending and curbing manipulation risks. By highlighting these questions, the article underscores the necessity of an appropriate conceptualisation of manipulation to ensure the responsible development of Generative AI technologies.

Humanity is officially one second closer to world annihilation, scientists say. The Doomsday Clock has been revealed – and it now sits at 89 seconds to midnight, one second closer than last year. It's also the closest the clock has ever been to midnight in its 78-year history, meaning we're nearer to world-ending catastrophe than ever before. The Bulletin of Atomic Scientists, which decides where the hands are set, cited the Russia-Ukraine war, ongoing conflicts in the Middle East, the threat of nuclear war, climate change, a looming bird flu pandemic and AI arms race for the update. The Chicago-based nonprofit created the Doomsday Clock in 1947 during the Cold War tensions that followed World War II to warn the public about how close humankind was to destroying the world.

A man who was piloting a drone that collided with a firefighting aircraft working on the Palisades fire has agreed to plead guilty to a misdemeanor, pay a fine and complete community service, federal prosecutors said Friday. Peter Tripp Akemann, 56, of Culver City was charged with unsafe operation of an unmanned aircraft. He could still face up to a year in federal prison, prosecutors said. The drone, which authorities say was flying in restricted airspace on Jan. 9, put a fist-sized hole in the left wing of a Super Scooper -- a massive fixed-wing plane that can drop large amounts of water onto a fire. The collision knocked the plane out of commission for about five days and destroyed the drone.

Beginning in 2023, the release of data-driven atmospheric forecasting models powered by deep neural network architectures began a revolution in medium-range weather forecasting, with some commenters [Bauer, 2024] anticipating that data-driven forecasting will soon supplant traditional numerical weather prediction (NWP) systems in all operational contexts. GraphCast [Lam et al., 2023], FourCastNet [Kurth et al., 2023], and Pangu-Weather [Bi et al., 2023] demonstrated forecast skill superior to that of the high-resolution forecast system (IFS) of the European Centre for Medium Range Weather Forecasts (ECMWF) at lead times (forecast lengths) up to 10 days. Since the publication of these models, the field has been joined by many others, including the Artificial Intelligence Forecasting System (AIFS) developed by ECMWF itself [Lang et al., 2024a]. From the standpoint of machine learning, atmospheric forecasting is a large-scale generative problem comparable to predicting the next frame of a video. As a typical example, the version of the GraphCast model deployed experimentally by the National Oceanic and Atmospheric Administration (NOAA) [NOAA, 2024] predicts the 6-hour forecast for six atmospheric variables at each of 13 vertical levels plus five surface variables, on a latitude/longitude grid, for about 86 million output degrees of freedom in aggregate. GraphCast takes two time-levels as input, so the input for this model has about 170 million degrees of freedom. These first-generation data-driven weather models generally act as deterministic forecast systems, where each unique initial condition is mapped to a single forecast and verified against a "ground truth" from a data analysis system. The ERA5 atmospheric reanalysis [Hersbach et al., 2020] of ECWMF is most often used as the source of initial and verifying data for these forecast systems owing to its high quality and consistent behaviour from 1979 to present.

The accelerating development and deployment of AI technologies depend on the continued ability to scale their infrastructure. This has implied increasing amounts of monetary investment and natural resources. Frontier AI applications have thus resulted in rising financial, environmental, and social costs. While the factors that AI scaling depends on reach its limits, the push for its accelerated advancement and entrenchment continues. In this paper, we provide a holistic review of AI scaling using four lenses (technical, economic, ecological, and social) and review the relationships between these lenses to explore the dynamics of AI growth. We do so by drawing on system dynamics concepts including archetypes such as "limits to growth" to model the dynamic complexity of AI scaling and synthesize several perspectives. Our work maps out the entangled relationships between the technical, economic, ecological and social perspectives and the apparent limits to growth. The analysis explains how industry's responses to external limits enables continued (but temporary) scaling and how this benefits Big Tech while externalizing social and environmental damages. To avoid an "overshoot and collapse" trajectory, we advocate for realigning priorities and norms around scaling to prioritize sustainable and mindful advancements.