Knowledge catalogue
The next version of Claude Code will introduce a `/usage` command that provides a detailed breakdown of token consumption across different components including Skills, Agents, MCPs (Model Context Prot
indicative although there are very important confounders here that have nothing to do with models https://x.com/swyx/status/2055231013253472418?s=20 also i think the publicly disclosed revenue time se
Individual use is small, but at aggregate scale, resource usage is higher. By 2030, AI may use as much electricity as Japan. Water use will remain less than 1% of total US water use in 2030, but that
arXiv:2605.20682v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have shown remarkable capability in bridging visual perception and textual reasoning, enabling zero-shot unders
arXiv:2603.22430v2 Announce Type: replace Abstract: Offline Reinforcement Learning (RL) learns optimal policies from fixed datasets, training a policy once and deploying it at inference time without f
arXiv:2603.15842v2 Announce Type: replace Abstract: Modern machine learning systems increasingly rely on sensitive data, creating significant privacy, security, and regulatory risks that existing priv
Infrawatch Ltd., a cybersecurity company providing intelligence about the infrastructure used by malicious actors to help organizations stop attacks, fraud and online abuse, announced Wednesday it has
arXiv:2605.21347v1 Announce Type: cross Abstract: Diagnosing failures in LLM agents remains largely manual. Practitioners inspect a small subset of execution traces, form ad-hoc hypotheses, and iterat
arXiv:2605.20257v1 Announce Type: new Abstract: Recently, instance discrimination models have emerged as a major solution for self-supervised learning. Having already demonstrated its effectiveness in
arXiv:2605.20799v1 Announce Type: cross Abstract: We present Overall FLOP Utilization (OFU), a hardware-level, precision-agnostic GPU efficiency metric for AI workloads on HPC systems, derived from tw
This post shows you how to use Amazon Bedrock AgentCore Runtime with Model Context Protocol (MCP) support to connect Amazon Quick with AWS services through the AWS API MCP Server, creating a conversat
Many healthcare organizations report that traditional worklist systems rely on rigid rules that ignore critical context, radiologist specialization, current workload, fatigue levels, and case complexi
arXiv:2605.20595v1 Announce Type: new Abstract: Dense low-altitude aerial operations require more than pre-flight route coordination and last-resort collision avoidance. Once aircraft are airborne, di
arXiv:2605.20784v1 Announce Type: cross Abstract: Spatial reasoning requires both location-bound computation and location-invariant structure: agents must make local moves while preserving route, obje
arXiv:2508.08636v2 Announce Type: replace Abstract: Large language models (LLMs) have revolutionized artificial intelligence by enabling complex reasoning capabilities. While recent advancements in re
arXiv:2605.20693v1 Announce Type: new Abstract: Interpretable text representations should expose coordinates that are not only predictive, but also meaningful enough for independent auditors to apply.
The sandbox Auth Proxy is a security mechanism designed to control and limit the interactions between AI agents and external systems by establishing a controlled boundary. This explainer from Harrison
arXiv:2605.20285v1 Announce Type: new Abstract: We tackle the question of how to scale more efficiently across the many, ever-growing stages of current LLM training pipelines. Our guiding intuition st
The financial services software company Intuit Inc., known for platforms that include Credit Karma, QuickBooks and TurboTax, said today it’s letting go 17% of its workforce, or about 3,000 people. The
AcuRite is discontinuing its My AcuRite app, citing obsolete technology and the unsustainability of maintaining two separate apps. The company stated that ongoing maintenance, security updates, and co
arXiv:2601.05877v3 Announce Type: replace Abstract: Recent work shows that large multimodal models (LMMs) can self-improve from unlabeled data via self-play and intrinsic feedback. Yet existing self-e
arXiv:2605.21475v1 Announce Type: new Abstract: Relational prediction tasks are fundamental in many real-world applications, where data are naturally stored in relational databases (RDBs). Relational
It is the answer This was my favorite moment from Elon, Franz, and Lars yesterday. Elon: 'I’ll tell you something, maybe at a fundamental level why the Model S/X succeeded, which is that, those cars w
arXiv:2605.20258v1 Announce Type: new Abstract: Contextual Integrity (CI) defines privacy not merely as keeping information hidden, but as governing information flows according to the norms of a given
It was an honor to give the keynote at MLSys Covered how AI systems have evolved, why AI is needed to improve them, why results have disappointed, why the future looks amazing, and why I’m working on
arXiv:2603.00086v2 Announce Type: replace Abstract: Automatic speech recognition for French medical conversations remains challenging, with word error rates often exceeding 30% in spontaneous clinical
arXiv:2605.21431v1 Announce Type: new Abstract: Video Virtual Try-On (VVT) aims to seamlessly replace a garment on a person in a video with a new one. While existing methods have made significant stri
It’s crazy that OpenAI and xAI were built partly as ways to mitigate @demishassabis’s power and how both are more reckless and less focused on the good part, viz AI for science. And then Anthropic was
This post likely clarifies the correct pronunciation of 'Hermes' (the Greek mythological messenger god and luxury brand), humorously highlighting a common mispronunciation among English speakers. The
Japan’s AI adoption growth is remarkable. In just a few days here, you can already see how different the perceptions around adoption and use cases are. Also, I love seeing books about Runway. Country-
CNBC: Jeff Bezos dismisses AI job fears, defends billionaires against “vilification”, proposes eliminating income taxes for low earners, and praises President Trump — VIDEO 54:38 — Watch CNBC's full i
arXiv:2605.20904v1 Announce Type: new Abstract: We propose JFAA, a JEPA-based Future Action Anticipation method for the EPIC-KITCHENS-100 (EK-100) Action Anticipation task. Inspired by the representat
arXiv:2605.20960v1 Announce Type: new Abstract: This paper introduces JobArabi, a large-scale corpus of Arabic job announcements collected from social media between January 2024 and October 2025. The
arXiv:2605.20648v1 Announce Type: new Abstract: Learning from Demonstration (LfD) enables robots to learn complex behaviors from expert examples, yet existing approaches often fail to generalize to ne
arXiv:2605.20284v1 Announce Type: new Abstract: Industrial anomaly detection has been significantly advanced by Large Multimodal Models (LMMs), enabling diverse human instructions beyond detection, pa
JUST IN: SpaceX pledges to cover all power grid infrastructure upgrade costs associated with its data centers so those costs are not passed on to local households, per its S-1 filing. JUST IN: COLOSSU
The James Webb Space Telescope has created the first weather map of the exoplanet WASP-94A b, located nearly 700 light-years from Earth, revealing that morning clouds make way for clear skies at night
Kafka, but for agents! i'm excited to open source Active Graph: an event-sourced reactive graph runtime for long-running, agents 🔄🧠 events/logs projects a graph. reactive behaviors react and affect th
arXiv:2506.16950v2 Announce Type: replace Abstract: Out-of-distribution (OOD) robustness is a desired property of computer vision models. Improving model robustness requires high-quality signals from
The unit of AI compute has shifted from single hosts to rack-scale systems that integrate NVIDIA GPUs, CPUs, scale-up networking fabrics, and liquid cooling, such as the NVIDIA GB300 NVL72 and NVIDIA
arXiv:2605.21235v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has become an effective paradigm for improving reasoning language models on tasks such as mathemat
arXiv:2603.23531v2 Announce Type: replace Abstract: Political polarization emerges from a complex interplay of beliefs about policies, figures, and issues. However, most computational analyses reduce
arXiv:2605.21292v1 Announce Type: cross Abstract: Gradient-flow analyses show that simplified linear transformers can learn the in-context linear-regression algorithm, but they do not explain the fini
arXiv:2605.21362v1 Announce Type: new Abstract: Jailbreak attacks expose a persistent gap between the intended safety behavior of aligned large language models and their behavior under adversarial pro
arXiv:2605.21478v1 Announce Type: new Abstract: Pose-driven full-body avatars built on neural rendering produce high-quality novel views of a captured subject. Yet loose clothing and other dynamic ele
arXiv:2605.20391v1 Announce Type: cross Abstract: Traditional anomaly detection marks events when measured signals cross predefined thresholds. This captures the moment of transition but not the struc
arXiv:2605.20547v1 Announce Type: new Abstract: Many recent flow-matching and diffusion-style generative models rely on auxiliary stochastic dynamics during training: a richer process is simulated to
arXiv:2605.20372v1 Announce Type: new Abstract: Multimodal semantic segmentation benefits remote sensing analysis by combining complementary information from different sensor modalities. In real-world
arXiv:2605.20244v1 Announce Type: cross Abstract: We present Lean Refactor, a plug-and-play retrieval-augmented agentic framework for multi-objective, controllable, and version-robust refactoring of L
arXiv:2605.20242v1 Announce Type: new Abstract: Efficient discovery of precursor additives is essential for improving the performance of perovskite solar cells, yet the large chemical space makes conv
Learn how to build LLM Wikis and LLM Artifacts. New VIDEO: From LLM Wikis to LLM Artifacts Shared all my thoughts on why LLM wikis and HTML artifacts are a big deal. Plus, new tools to help you build
Replit Enterprise is a commercial offering from Replit designed for organizations and businesses seeking advanced collaborative coding and development capabilities on the Replit platform. This likely
arXiv:2512.08013v2 Announce Type: replace-cross Abstract: Reliable optimal control is challenging when the dynamics of a nonlinear system are unknown and only infrequent, noisy output measurements are
arXiv:2605.21160v1 Announce Type: new Abstract: The discovery of first integrals is of fundamental scientific importance for understanding conservation laws in dynamical systems. However, existing sym
arXiv:2605.20883v1 Announce Type: new Abstract: Dictionary learning is a powerful tool for creating interpretable representations. When applied to functional magnetic resonance imaging (fMRI) data, th
arXiv:2601.22292v2 Announce Type: replace-cross Abstract: Multi-agent social dilemmas, such as the tragedy of the commons, capture settings where individual incentives conflict with collective well-be
arXiv:2602.06025v2 Announce Type: replace Abstract: Memory is increasingly central to Large Language Model (LLM) agents operating beyond a single context window, yet most existing systems rely on offl
arXiv:2605.21330v1 Announce Type: new Abstract: In-hand object manipulation is a fundamental yet challenging capability for dexterous robots. Despite significant progress in dexterous manipulation, ex
arXiv:2605.21258v1 Announce Type: new Abstract: Current 3D-aware pretraining methods for embodied perception and manipulation are largely built on differentiable rendering frameworks, producing either
arXiv:2601.22538v2 Announce Type: replace Abstract: Learning-to-defer (L2D) routes each decision to a system's own predictor or to an external expert. Streaming time-series settings break the offline-