Large Language Models (LLMs) excel at tasks like language processing, strategy games, and reasoning but struggle to build generalizable internal representations essential for adaptive decision-making in agents. For agents to effectively navigate complex environments, they must construct reliable world models. While LLMs perform well on specific benchmarks, they often fail to generalize, leading to brittle representations that limit their real-world effectiveness. Understanding how LLMs build internal world models is key to developing agents capable of consistent, adaptive behavior across tasks. We analyze OthelloGPT, a GPT-based model trained on Othello gameplay, as a controlled testbed for studying representation learning. Despite being trained solely on next-token prediction with random valid moves, OthelloGPT shows meaningful layer-wise progression in understanding board state and gameplay. Early layers capture static attributes like board edges, while deeper layers reflect dynamic tile changes. To interpret these representations, we compare Sparse Autoencoders (SAEs) with linear probes, finding that SAEs offer more robust, disentangled insights into compositional features, whereas linear probes mainly detect features useful for classification. We use SAEs to decode features related to tile color and tile stability, a previously unexamined feature that reflects complex gameplay concepts like board control and long-term planning. We study the progression of linear probe accuracy and tile color using both SAE's and linear probes to compare their effectiveness at capturing what the model is learning. Although we begin with a smaller language model, OthelloGPT, this study establishes a framework for understanding the internal representations learned by GPT models, transformers, and LLMs more broadly. Our code is publicly available: https://github.com/ALT-JS/OthelloSAE.

Here, we present the outcomes from the second Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistry, which engaged participants across global hybrid locations, resulting in 34 team submissions. The submissions spanned seven key application areas and demonstrated the diverse utility of LLMs for applications in (1) molecular and material property prediction; (2) molecular and material design; (3) automation and novel interfaces; (4) scientific communication and education; (5) research data management and automation; (6) hypothesis generation and evaluation; and (7) knowledge extraction and reasoning from scientific literature. Each team submission is presented in a summary table with links to the code and as brief papers in the appendix. Beyond team results, we discuss the hackathon event and its hybrid format, which included physical hubs in Toronto, Montreal, San Francisco, Berlin, Lausanne, and Tokyo, alongside a global online hub to enable local and virtual collaboration. Overall, the event highlighted significant improvements in LLM capabilities since the previous year's hackathon, suggesting continued expansion of LLMs for applications in materials science and chemistry research. These outcomes demonstrate the dual utility of LLMs as both multipurpose models for diverse machine learning tasks and platforms for rapid prototyping custom applications in scientific research.

Large-language models (LLMs) such as GPT-4 caught the interest of many scientists. Recent studies suggested that these models could be useful in chemistry and materials science. To explore these possibilities, we organized a hackathon. This article chronicles the projects built as part of this hackathon. Participants employed LLMs for various applications, including predicting properties of molecules and materials, designing novel interfaces for tools, extracting knowledge from unstructured data, and developing new educational applications. The diverse topics and the fact that working prototypes could be generated in less than two days highlight that LLMs will profoundly impact the future of our fields. The rich collection of ideas and projects also indicates that the applications of LLMs are not limited to materials science and chemistry but offer potential benefits to a wide range of scientific disciplines.

Many amputees throughout the world are left with limited options to personally own a prosthetic arm due to the expensive cost, mechanical system complexity, and lack of availability. The three main control methods of prosthetic hands are: (1) body-powered control, (2) extrinsic mechanical control, and (3) myoelectric control. These methods can perform well under a controlled situation but will often break down in clinical and everyday use due to poor robustness, weak adaptability, long-term training, and heavy mental burden during use. This paper lays the complete outline of the design process of an affordable and easily accessible novel prosthetic arm that reduces the cost of prosthetics from $10,000 to $700 on average. The 3D printed prosthetic arm is equipped with a depth camera and closed-loop off-policy deep learning algorithm to help form grasps to the object in view. Current work in reinforcement learning masters only individual skills and is heavily focused on parallel jaw grippers for in-hand manipulation. In order to create generalization, which better performs real-world manipulation, the focus is specifically on using the general framework of Markov Decision Process (MDP) through scalable learning with off-policy algorithms such as deep deterministic policy gradient (DDPG) and to study this question in the context of grasping a prosthetic arm. We were able to achieve a 78% grasp success rate on previously unseen objects and generalize across multiple objects for manipulation tasks. This work will make prosthetics cheaper, easier to use and accessible globally for amputees. Future work includes applying similar approaches to other medical assistive devices where a human is interacting with a machine to complete a task.

We outline the design and construction of novel robotic arms using machine perception, convolutional neural networks, and symbolic AI for logical control and affordance indexing. We describe our robotic arms built with a humanlike mechanical configuration and aesthetic, with 28 degrees of freedom, touch sensors, and series elastic actuators. The arms were modelled in Roodle and Gazebo with URDF models, as well as Unity, and implement motion control solutions for solving live games of Baccarat (the casino card game), rock paper scissors, handshaking, and drawing. This includes live interactions with people, incorporating both social control of the hands and facial gestures, and physical inverse kinematics (IK) for grasping and manipulation tasks. The resulting framework is an integral part of the Sophia 2020 alpha platform, which is being used with ongoing research in the authors work with team AHAM, an ANA Avatar Xprize effort towards human-AI hybrid telepresence. These results are available to test on the broadly released Hanson Robotics Sophia 2020 robot platform, for users to try and extend.