Models

Armin Ronacher, in an excerpt quoted by Simon Willison, discusses how the shared language of a software project is not English or Python but a common understanding of concepts, boundaries, invariants, ownership, and system shape. He argues that before AI agents, this understanding was maintained through friction (reading code, asking questions, coordinating), which, while partly wasteful, was a crucial process for synchronizing people.

Meta prompting is a technique where a prompt is used to create, improve, or control another prompt. It shifts the model from direct task execution to prompt design, improving consistency and scalability for repeated tasks.

Google now uses your images, voice searches, and videos from search interactions to train its AI models. You can opt out to protect your privacy. Here's how.

Open models like NVIDIA Nemotron enable enterprises to build AI that uniquely addresses their business needs, offering full control, customization, and cost efficiency, driving the shift from AI adoption to AI ownership.

Researcher Dave Kuszmar discovered multiple systemic vulnerabilities that let him bypass LLM safety and obtain dangerous instructions. These exploits worked across nearly all major LLMs, revealing an industry-wide security problem. Kuszmar calls for slowing deployment, increasing transparency, and large-scale research into LLM safety before further integrating these systems into society.

An exploration of the historical links between semiotics and large language models, drawing on thinkers like Saussure, Barthes, and Derrida to analyze the relationship between linguistic signs and AI-generated content.

Mistral AI introduces a vision model that enables robots to navigate unknown environments using only a single RGB camera and natural language instructions.

Mnemo AI is a local agentic AI assistant built with LangGraph and LangChain, supporting multiple LLM providers including Ollama, Bedrock, OpenAI, Anthropic, and more. It features MCP tool integration, RAG, user profile learning, episodic memory, and an ACE Playbook that learns from both successes and failures. The tool also offers web search, image analysis, file operations, bash execution, and many other capabilities.

Scaling LLMs isn’t about adding GPUs. It’s about removing wasted work from every request.

Demis Hassabis, CEO of Google DeepMind, proposes a global AI watchdog with the power to halt dangerous frontier models. He argues the US should lead the effort and hopes to establish the organization by year-end.

Hayden Bleasel has released Blume, an open-source, MIT-licensed documentation framework. It reads a folder of Markdown or MDX and generates a hidden Astro project, shipping static, AI-ready docs with local search, 30+ MDX components, llms.txt, and a built-in MCP server.

Mistral AI introduced Robostral Navigate, an 8B embodied navigation model. It moves robots from a plain-language instruction using only a single RGB camera, with no LiDAR or depth sensors. The model reaches 76.6% success on R2R-CE validation unseen through a pointing method, prefix-caching training, and CISPO online reinforcement learning.

This paper proposes a human-efficient post-training pipeline that enables a small number of human operators to supervise multiple robots through specialized division of labor and automatic trajectory segmentation using VLAC-CUT. Validated on four real-world manipulation tasks, the final policies achieve 80%-95% success rates and improve task throughput by 1.7x-4.2x over the base model.

This paper proposes a risk-field enhanced closed-loop digital twin framework for safety validation of autonomous driving systems. The framework integrates physical data acquisition, virtual reconstruction, risk-aware scenario generation, and algorithm evaluation, using a driving risk field as a unified intermediate representation to identify high-risk scenarios and provide safety guidance for reinforcement learning policies. Experiments show the method improves targeted validation and interpretability, but its effectiveness is bounded by model fidelity and sim-to-real transfer.

UAV swarms have potential in SAR and environmental monitoring but face limitations in situational awareness, connectivity, and cybersecurity. This paper proposes LAUS, an LLM-centric agentic AI framework integrating perception, memory, reasoning, and action for adaptive swarm behavior. It reviews enabling technologies, analyzes threats like Priority Manipulation Attacks, and identifies open challenges including hallucination-resistant reasoning, onboard LLM deployment under SWaP constraints, and standardized security benchmarks.

EgoSteer is a full-stack system that enables steerable dexterous manipulation by pre-training a VLA model on 9.6K hours of egocentric human videos and post-training on robots. It achieves robust execution of free-form instructions across 40+ tasks, with failure recovery and few-shot adaptation to long-horizon tasks like box folding at 75%+ success.

Real-image diffusion inversion faces a quality-cost trade-off. This paper reveals two mechanisms: element-wise compression asymmetry and trajectory binding, leading to Noise-Anchored Reverse Correction (NARC), a training-free method that outperforms baselines with drastically reduced storage.

A paper accepted at ECCV 2026 presents a new approach to wearable motion capture that works with any combination of consumer devices like smartphones and smartwatches, introducing the WHIP model and a comprehensive dataset spanning 50 activities, along with a systematic study of sensor complementarity.

Multi-Modal Knowledge Graphs (MMKGs) enrich entities with modalities like text and images, but entities with highly similar multi-modal features remain hard to distinguish. Temporal information can serve as an additional modality for disambiguation, yet existing approaches rarely treat time as a separate modality due to sparse temporal semantics and noise from multiple timestamps. This paper proposes Time Imprint, a framework that treats time as an entity-level modality and aligns temporal, textual, and visual representations via a three-view contrastive objective. It also designs a compact timestamp subset selection with attention pooling to balance specificity and robustness. Experiments on three MMKG benchmarks show state-of-the-art link prediction, with Hits@1 improvements up to 6.07% overall and 58% on the top-1% ambiguous samples.

This paper presents the first demonstration of a low-power MCU-based edge device for Automatic License Plate Recognition (ALPR). It uses a 9-core RISC-V processor (GAP8) with a QVGA ultra-low-power grayscale imager, employing SSDlite-MobilenetV2 for detection (38.9% mAP) and LPRNet for recognition (>99.13%). The system achieves 1.09 FPS at 117 mW, is 73x more energy-efficient than a Raspberry Pi 3 solution, and works on license plates as small as 30x5 pixels.

A new AI system called ReflectWorld-MM enables assistants to continuously process and remember open-ended video streams by organizing memory around persistent entities rather than frames, achieving state-of-the-art results on six benchmarks.

RSLoRA is a training-free, gradient-free method for allocating LoRA ranks based on activation-space geometry. It introduces virtual representational probing to identify high-sensitivity layers, outperforming state-of-the-art allocators like AdaLoRA and GoRA.

WiCAT, a multi-subject model using self-supervised pretraining, outperforms single-session models and enables zero-shot behavior decoding on unseen subjects in widefield calcium imaging.

Researchers propose DUNE, a training-free framework that refines diffusion models by detecting and suppressing early-stage fluctuations in deep latents, reducing artifacts and hallucinations while improving fidelity across both U-Net and Transformer backbones.

This paper investigates the feasibility of training a reasoning language model in Japanese. By applying GRPO to a Japanese continually pretrained model based on Qwen-3-Swallow-8B, the authors find that reasoning-language control is achievable, yet performance at best matches English-reasoning baselines. On Japanese cultural benchmarks, the model performs worse, indicating that reasoning in Japanese does not automatically improve culturally relevant tasks.

This work adapts an open-source spoken language model (SLM) to the Singaporean Home Team domain using LoRA fine-tuning, a surrogate text-QA dataset, and a multi-task objective with CoBa reweighting. The resulting model, HT-Moonstone (5B), matches or outperforms SLMs 7x its size on most tasks and achieves top accent and gender recognition with less than 2% loss in original speech QA ability.

A new study shows that post-training quantization can silently alter how large language models reason even when task accuracy is preserved. Using a six-category failure taxonomy, the researchers classified 30,000 chain-of-thought outputs and found that hollow convergence exhibits a size-dependent shift under NF4 quantization, while shortcut collapse and confidence snowballing undergo qualitative changes. Hollow convergence cannot be reliably detected from surface-level text features, posing a deployment risk.

This report studies on-device English-to-Traditional-Chinese subtitle translation for Taiwan under short inputs, short outputs, batch-size-one inference, low latency, and privacy constraints. The authors replace the original 151k-token vocabulary with a 64k-token subtitle-domain tokenizer, perform embedding calibration and fine-tuning, achieving a 59.2% tie-excluded win rate against Google Translate on a subset of OpenSubtitles2024, and a 1.63x speedup on Apple M2.

A new benchmark framework evaluates the faithfulness of LLM-generated clinical trial summaries across three stakeholder audiences. Using 200 stratified trials from ClinicalTrials.gov and a six-dimension annotation schema, the study identifies 'Unsupported Claims' as the dominant failure mode. A knowledge-graph-augmented retrieval system shows statistically significant improvements in faithfulness scores.

A language-model forecasting system for merger arbitrage, utilizing long-context reasoning over technical documents, outperforms market-implied probabilities and frontier LLMs on a dataset of over 400 large deals across 42 countries.

Bilibili releases Index-1.9B, a series of open small language models with competitive performance on benchmarks.

CLIR-Bench is a benchmark for evaluating models on question answering over irregular clinical time series. It is constructed from de-identified ICU records using a principled four-stage pipeline, comprising 6,600 QA instances covering 11 clinical variables, organized into four capability dimensions and 11 tasks. Experiments reveal that current generalist models struggle to retrieve and reason over sparse clinical evidence, highlighting the need for stronger irregular time-series reasoning methods.

Researchers introduce a reference-based membership inference method to detect whether large language models are distilled from other models. By comparing a student model's preference for outputs from different candidate teachers against an earlier checkpoint, the method identifies the most likely teacher with near-perfect accuracy, handling unknown distillation pipelines and open-world settings.

A new study reveals that coding agents need minimal context when editing code: the signal is only in the code being edited, natural-language summaries fail to answer behavioral questions, surrounding context (UML skeletons) performs no better than deleting it, and compressed context matches full files at one-third the tokens. Temperature-0 inference introduces a ~9% noise floor. The authors release their instrument including gold-validated environments, deterministic patches, and pre-registered hypotheses.

A new paper introduces MawForge, a system that enables practical local inference of Sparse Mixture-of-Experts (MoE) language models on memory-constrained unified-memory machines by storing the model on disk and materializing expert tensors on demand into a bounded cache. The system is effective as a measurement substrate but not as a cache-maximization policy.

This paper proposes a novel two-level taxonomy for GNN-based knowledge graph technologies, covering construction, embedding, reasoning, and applications, and reviews various GNN models, discussing their strengths, limitations, and future directions.

This paper presents a closed-loop control framework using a small language model (SLM) aligned via Group Relative Policy Optimization (GRPO). The system integrates an action agent, a digital-twin validator, and a reprompting agent to iteratively correct outputs. In thermal control simulations, it achieves 91.5% action-alignment accuracy with 3.84s inference latency, demonstrating viability for edge autonomous control.

YUKTI is a novel framework for robust decision-making from natural language, using uncertainty-typed proposition graphs and Assumption-Robust Pareto Frontiers (ARPF). It reduces mean and tail regret by over 90% under misspecification, outperforms a status-quo baseline by 34% on a real dataset, and incurs 47x less regret than an LLM-based approach.

A new study investigates how message format affects information fidelity in multi-hop LLM agent relays, finding that effects are tier-dependent. Under strong relays with faithful instructions, loss is minimal, while weak relays show large inter-format variability. Structured formats provide a faithful, error-localizing channel, not an error-correcting code.

This study introduces the Format Sensitivity Index (FSI) and Parseability Sensitivity Index (PSI) to measure how prompt wrappers affect LLM accuracy and answer parseability. Experiments on 140,000 generations show mean FSI varies by over 30x across models, largely explained by compliance failures. Parseability remains a strong predictor of accuracy even after controlling for task, model, and wrapper. Recommendations for robust benchmarking and structured-output deployments are provided.

This paper proposes a structured diagnostic assistance framework based on the Toulmin model of argumentation, decomposing image-based ML diagnoses into claim, grounds, warrant, qualifier, rebuttal, and backing. Using a specialized biomarker extractor, a MedGemma agent for medical knowledge, and MedSigLip for image similarity, the system presents human experts with interpretable components for critical assessment of ML outputs.

A new book claims AI has been built on a flawed assumption dating back to Alan Turing's famous 1950 paper. Peter J. Denning argues that the most important parts of human intelligence, including common sense, intuition, culture, and practical know-how, cannot be encoded into computers. He believes this makes true human-level AI impossible, regardless of how large language models become.

Anthropic has launched Claude Sonnet 5, its most agentic mid-tier model, outperforming Sonnet 4.6 across all benchmarks and narrowing the gap to Opus 4.8. It introduces effort levels to control reasoning costs, offering great value at low/medium effort but potentially exceeding Opus 4.8 cost at extra-high effort. It is now the default model for Free and Pro plans and accessible via API.

Apple Music serves listeners across 150+ storefronts in dozens of languages, with a catalog that grows by hundreds of thousands of new tracks daily. At this scale, search recall on misspelled, transliterated, and cross-lingual queries becomes a dominant driver of session quality. Apple researchers present a multilingual semantic retrieval system built on a 305M-parameter Siamese bi-encoder fine-tuned from GTE-multilingual-base with curriculum-scheduled multi-objective training. The system achieves a 69% relative improvement in Hit@10 offline, and in a worldwide online A/B test, a 2.28% conversion-rate lift overall with an 86% reduction in no-result rate. Tail queries see a 7.93% relative CR lift.

Peter Gostev created DOOMQL, a Doom-like game that uses SQLite as the game engine, featuring a recursive CTE ray tracer. Simon Willison demonstrates how to play it and build a Datasette app to view the game state in real time.

Simon Willison shares a GitHub code frequency chart for his Datasette open source project, illustrating the impact of coding agents and Opus 4.5-class models, with a huge spike in activity in 2026 aligned with releases like Opus 4.8, GPT-5.5, Fable 5, and GPT-5.6 Sol.

OpenAI's latest family of models, GPT-5.6 Sol, Terra, and Luna, is now generally available on Amazon Bedrock. Sol is a flagship reasoning model with state-of-the-art performance, Terra offers balanced capabilities for production, and Luna provides fast, low-cost inference. Amazon Bedrock's next-gen inference engine provides burst handling, prompt caching with 90% discount, and hardware-enforced security. Additionally, OpenAI launched ChatGPT Work and Codex agents.

System 2 Arena provides objective AI strategy benchmarks through gaming environments.

A journey through the evolution of distillation for frontier models.

Outlines is an open-source library that introduces deterministic certainty into LLMs' output generation process for better, more reliable generation of structured outputs.