Learning from AI feedback (LAIF) is a popular paradigm for improving the instruction-following abilities of powerful pre-trained language models. LAIF first performs supervised fine-tuning (SFT) using demonstrations from a teacher model and then further fine-tunes the model with reinforcement learning (RL) or direct preference optimization (DPO), using feedback from a critic model. While recent popular open-source models have demonstrated substantial improvements in performance from the RL step, in this paper we question whether the complexity of this RL step is truly warranted for AI feedback. We show that the improvements of the RL step are virtually entirely due to the widespread practice of using a weaker teacher model (e.g. GPT-3.5) for SFT data collection than the critic (e.g., GPT-4) used for AI feedback generation.

Artificial intelligence is rapidly evolving towards multi-agent systems where numerous AI agents collaborate and interact with external tools. Two key open standards, Google's Agent to Agent (A2A) protocol for inter-agent communication and Anthropic's Model Context Protocol (MCP) for standardized tool access, promise to overcome the limitations of fragmented, custom integration approaches. While their potential synergy is significant, this paper argues that effectively integrating A2A and MCP presents unique, emergent challenges at their intersection, particularly concerning semantic interoperability between agent tasks and tool capabilities, the compounded security risks arising from combined discovery and execution, and the practical governance required for the envisioned "Agent Economy". This work provides a critical analysis, moving beyond a survey to evaluate the practical implications and inherent difficulties of combining these horizontal and vertical integration standards. We examine the benefits (e.g., specialization, scalability) while critically assessing their dependencies and trade-offs in an integrated context. We identify key challenges increased by the integration, including novel security vulnerabilities, privacy complexities, debugging difficulties across protocols, and the need for robust semantic negotiation mechanisms. In summary, A2A+MCP offers a vital architectural foundation, but fully realizing its potential requires substantial advancements to manage the complexities of their combined operation.

Social platforms have expanded opportunities for deliberation with the comments being used to inform one's opinion. However, using such information to form opinions is challenged by unsubstantiated or false content. To enhance the quality of opinion formation and potentially confer resistance to misinformation, we developed Iffy-Or-Not (ION), a browser extension that seeks to invoke critical thinking when reading texts. With three features guided by argumentation theory, ION highlights fallacious content, suggests diverse queries to probe them with, and offers deeper questions to consider and chat with others about. From a user study (N=18), we found that ION encourages users to be more attentive to the content, suggests queries that align with or are preferable to their own, and poses thought-provoking questions that expands their perspectives. However, some participants expressed aversion to ION due to misalignments with their information goals and thinking predispositions. Potential backfiring effects with ION are discussed.

Molecular dynamics (MD) simulation techniques are widely used for various natural science applications. Increasingly, machine learning (ML) force field (FF) models begin to replace ab-initio simulations by predicting forces directly from atomic structures. Despite significant progress in this area, such techniques are primarily benchmarked by their force/energy prediction errors, even though the practical use case would be to produce realistic MD trajectories. We aim to fill this gap by introducing a novel benchmark suite for ML MD simulation. We curate representative MD systems, including water, organic molecules, peptide, and materials, and design evaluation metrics corresponding to the scientific objectives of respective systems. We benchmark a collection of state-of-the-art (SOTA) ML FF models and illustrate, in particular, how the commonly benchmarked force accuracy is not well aligned with relevant simulation metrics. We demonstrate when and how selected SOTA methods fail, along with offering directions for further improvement. Specifically, we identify stability as a key metric for ML models to improve. Our benchmark suite comes with a comprehensive open-source codebase for training and simulation with ML FFs to facilitate further work.

Purpose: Object detection is rapidly evolving through machine learning technology in automation systems. Well prepared data is necessary to train the algorithms. Accordingly, the objective of this paper is to describe a re-evaluation of the so-called Logistics Objects in Context (LOCO) dataset, which is the first dataset for object detection in the field of intralogistics. Methodology: We use an experimental research approach with three steps to evaluate the LOCO dataset. Firstly, the images on GitHub were analyzed to understand the dataset better. Secondly, Google Drive Cloud was used for training purposes to revisit the algorithmic implementation and training. Lastly, the LOCO dataset was examined, if it is possible to achieve the same training results in comparison to the original publications. Findings: The mean average precision, a common benchmark in object detection, achieved in our study was 64.54%, and shows a significant increase from the initial study of the LOCO authors, achieving 41%. However, improvement potential is seen specifically within object types of forklifts and pallet truck. Originality: This paper presents the first critical replication study of the LOCO dataset for object detection in intralogistics. It shows that the training with better hyperparameters based on LOCO can even achieve a higher accuracy than presented in the original publication. However, there is also further room for improving the LOCO dataset.

Wrist Fracture is the most common type of fracture with a high incidence rate. Conventional radiography (i.e. X-ray imaging) is used for wrist fracture detection routinely, but occasionally fracture delineation poses issues and an additional confirmation by computed tomography (CT) is needed for diagnosis. Recent advances in the field of Deep Learning (DL), a subfield of Artificial Intelligence (AI), have shown that wrist fracture detection can be automated using Convolutional Neural Networks. However, previous studies did not pay close attention to the difficult cases which can only be confirmed via CT imaging. In this study, we have developed and analyzed a state-of-the-art DL-based pipeline for wrist (distal radius) fracture detection—DeepWrist, and evaluated it against one general population test set, and one challenging test set comprising only cases requiring confirmation by CT. Our results reveal that a typical state-of-the-art approach, such as DeepWrist, while having a near-perfect performance on the general independent test set, has a substantially lower performance on the challenging test set—average precision of 0.99 (0.99–0.99) versus 0.64 (0.46–0.83), respectively. Similarly, the area under the ROC curve was of 0.99 (0.98–0.99) versus 0.84 (0.72–0.93), respectively. Our findings highlight the importance of a meticulous analysis of DL-based models before clinical use, and unearth the need for more challenging settings for testing medical AI systems.

What do people who work in machine learning and AI think of actress Kristen Stewart's research paper on AI? originally appeared on Quora: the place to gain and share knowledge, empowering people to learn from others and better understand the world. There are perhaps two different questions to answer here: (1) What do we think of the paper? Let me address the second question first, because I think that is the root of the (possible) problem. As most things surrounding AI these days there is of course some hype effect and I understand how general publications would fall for a paper that manages to put together AI and a Hollywood actress. That said, I found Quartz approach was good and harmful enough.

The purpose of my book is to present arguments for this position, and to investigate its implications. Chapters discuss: models and semantic theories (with critical evaluations of work by Arturo Rosenblueth and Norbert Wiener, Brian Cantwell Smith, and Marx W. Wartofsky) the nature of "syntactic semantics" (including the relevance of Antonio Damasio's cognitive neuroscientific theories), conceptual-role semantics (with critical evaluations of work by Jerry Fodor and Ernest Lepore, Gilbert Harman, David Lewis, Barry Loewer, William G. Lycan, Timothy C. Potts, and Wilfrid Sellars), the role of negotiation in interpreting communicative acts (including evaluations of theories by Jerome Bruner and Patrick Henry Winston), Hilary Putnam's and Jerry Fodor's views of methodological solipsism, implementation and its relationships with such metaphysical concepts as individuation, instantiation, exemplification, reduction, and supervenience (with a study of Jaegwon Kim's theories), John Searle's Chinese-Room Argument and its relevance to understanding Helen Keller (and vice versa), and Herbert Terrace's theory of naming as a fundamental linguistic ability unique to humans. Throughout, reference is made to our implemented computational theory of cognition: a computerized cognitive agent implemented in SNePS.