Intel 情報源

IFM/K2-Horizon-MoVA-36B-A4B-GGUF

Extinct Tasmanian tiger's 'snap' unlike any living mammal's bite

Nvidia to Acquire Hugging Face

9 Mothers (YC P26) Is Hiring in Austin, TX

How Swiss tables work in Go built-in map

Sky Map 2000 – Star Atlas and Planetarium

A dark horse enters China's AI race: StartLux

Google Antigravity TOS: 3rd party usage can get Google account suspended

Audacity 4.0

Please don't rearrange our shoes when we turn up, paramedics in Japan urge

Meta, Google join the AI launch party

PLUS: Nail job interviews with the “Proof Project” method

Claude for Commerce Agents

Japan halves speed limit to 30km/h on all narrow city streets

Your Racist Linux Distro Is Very Nice (Scott Jennings)

People that worked on the same idea for decades

Tension wood: A 'muscle' that can both bend and straighten plants

Three schoolgirls in Kinsale pulled up a pea plant covered in warts (2016)

Pre-Release of Polars 2.0

inclusionAI/Ling-3.0-flash-Fin

Ask HN: Advice on Migrating from 1Password?

RSA-260 Factorized

IBM Quantum Nighthawk R2

[AINews] Muse Spark 1.3 matches GPT-5.6-Sol, confirming Meta Superintelligence as the newest Frontier Lab, >90% discount for training

an epic comeback story for Meta

Dutch central bank moves 86 tonnes of gold from US citing 'geopolitical unrest'

荷蘭央行將86噸黃金從美國運回，因…

Write Software in Latin (2025) [video]

Kakistocracy

解釋 kakistocracy 一詞，意指由…

It's Like Having 150 Extra Engineers

描述增加150名工程師的好處…

METR Report on OpenAI / Hugging Face Hacking Incident

Launch HN: RonanRX (YC S26) – Personalized Peptides and GLP-1s

Reasons robotics is hard

Uber shuts operations in Nigeria and Uganda with immediate effect

Nango (YC W23) is hiring across eng, product and GTM (SF and remote)

Is There I/O After Death? What Happens to Io_uring When a Process Dies

Mamdani Bans AI in NYC Schools

Vidact – a compiler that turns React into direct DOM operations

llm-openrouter 0.7.1

Release: llm-openrouter 0.7.1 Performance fix for loading OpenRouter models. Thanks, waveplate . #59 Tags: llm , openrouter

Music Theory for Programmers

Altair Basic Interpreter Source Code (1975) [pdf]

The Silo · interactive 3D cutaway

I wanna live an NPC life

Fable 5.1 World Modeling

The Post-AI Internet Doesn't Look Great

Muse Spark 1.3

Introducing Muse Spark 1.3

llm 0.34

Release: llm 0.34 One new feature: llm logs --usage Markdown output now includes the response duration in milliseconds and as a human-readable duration. llm logs --short includes a new duration_ms field. #1653 Plus several contributed bug fixes, and a significant performance impr…

Unified Arabic

Black Hole of Los Alamos Seller of surplus nuclear research materials (2011)

The American Worker vs. the Most Qualified

Qantas Airbus A380 engine failure in 2010 (2023)

Async Rust vs RTOS showdown (2022)

A Million Falcons Went Missing. Here’s How They Were Found

I Don't Think I Can Stay in Tech

Electronic skin for prosthetics to sense temperature and pressure

A Common Measure of Communication for Speech Brain-Computer Interfaces

Speech brain-computer interfaces (speech BCIs) translate neural activity into language, offering a path towards restoring speech for people with paralysis and, more broadly, enabling new forms of natural human-computer interaction. Despite this promise, the field lacks a common measure of progress because systems use different datasets, recording methods, types of speech, and vocabularies, so their reported scores are rarely comparable. Underlying this measurement problem are two unresolved questions: (i) what distribution of words should a speech BCI enable a user to communicate, and (ii) how much information from this distribution can a system convey. We address both by deriving open-vocabulary mutual information (OVMI), an information-theoretic quantity that measures the information conveyed by a decoder relative to a reference distribution over the words a user may wish to communicate. This allows capabilities measured under different conditions, such as distinct vocabularies, to be evaluated on a common communication scale. We show that ordinarily reported accuracy, word error rate (WER), and other metrics computed only over the words a system supports can overstate how much of a user's intended speech the system can communicate. We then use OVMI to compare existing systems, expose trade-offs between how much of the user's language a system supports and how accurately it decodes those words, show that these comparisons depend on what the user is expected to communicate, and demonstrate that selecting a vocabulary to maximise OVMI yields up to 16.3% relative improvement in accuracy across three speech domains. OVMI therefore provides the speech BCI community with a principled way to compare heterogeneous systems, improve vocabulary design, and measure progress in the field.

Discriminative World Models for Web Agents

Recent web agents use world models for test-time action selection by sampling candidate actions, predicting the resulting web states, and ranking them with a ranker model or a Process Reward Model (PRM). These world models are typically trained via supervised next-state prediction to generate fixed representations like HTML or AXTree snapshots. However, this objective is misaligned with the downstream ranker, which relies on predicted states being discriminative across candidates to accurately score them. To address this, we introduce predicted-state matching, a training objective where the predicted representation must distinguish the true resulting state from those reached by alternative actions. We train these models using a branching web-agent dataset derived from WebArena Go-Browse trajectories, where every decision point contains multiple alternative actions and their resulting states. Experiments on our held-out predicted-state matching benchmark show that our approach outperforms world models trained with supervised next-state prediction. We further show that our approach improves PRM-style action ranking on WebPRMBench compared with action-only PRMs and PRMs augmented with supervised-next-state world models. Finally, on WebArena-Lite, using our world model for test-time action selection improves end-to-end task success. Our project page is available at: https://dhruvpendharkar.github.io/dwm/.

llm-anthropic 0.28

Release: llm-anthropic 0.28 Claude Fable 5.1 , reasoning traces are now displayed by default for models that support them, plus a new llm_anthropic.ClaudeRefusal exception for when Claude throws a refusal. Tags: llm , anthropic , claude , claude-mythos-fable

GRADSOLVE: fast exact gradients for ODE ensembles on GPUs

Ordinary differential equations (ODEs) underlie models in science and engineering, and many applications need derivatives of their solutions with respect to parameters. Ensembles of independent trajectories suit graphics processing units (GPUs), but current GPU software forces a trade-off: the fastest ensemble solvers cannot be differentiated in reverse mode at the speed they solve, and the solvers built for differentiation solve more slowly. No single tool has yet offered a reverse-mode gradient at the speed of a fused-kernel solve. We present GRADSOLVE, an open-source JAX library for solving and reverse-mode differentiating low-dimensional ODE ensembles on NVIDIA GPUs. It records the steps an adaptive solver accepts and differentiates a fixed-step replay of them; the returned gradient is the exact discrete adjoint of those steps, the same derivative Diffrax returns by default, obtained more cheaply from a fixed-length chain than from an adaptive loop. It targets ensembles differentiated many times against one recorded mesh, keeps Diffrax as a fallback, and supports explicit and Rosenbrock integrators. Used as a solver, GRADSOLVE's forward-only kernel ran 2.8x faster than DiffEqGPU.jl; used for gradients, once a record exists, it computed them 5.6-14.1x faster than Diffrax's checkpointed adjoint at matched forward-state accuracy across three GPU generations, the advantage narrowing on large ensembles and, on stiff systems, down to parity at tight accuracy. GRADSOLVE is released at https://github.com/ECLIPSE-AI4Science/gradsolve.

I Don't Have a Smartphone

Earth's organisms developed via evolution. What if the cosmos did, too?

Towards Trustworthy Autonomous Robots: An Explainable AI-Based Decision Framework

Autonomous robots powered by deep learning face a fundamental auditability challenge: when incidents occur, investigators cannot reconstruct why the system made specific decisions. This paper presents TRACE (Transparent Reasoning Architecture for Credible Execution), a decision framework that ensures every autonomous action can be traced back to sensor evidence through documented causal chains. The framework organizes decision-making into four auditable layers: Semantic Perception for evidence-grounded entity recognition, Belief Reasoning for probabilistic state estimation with causal graphs, Action Synthesis for constraint-aware planning with counterfactual documentation, and Execution Verification for compliance monitoring. TRACE is model-agnostic yet designed to integrate learning-based perception modules (CNNs, transformers) while preserving decision-level auditability. We evaluate the framework using three objective metrics: Evidence Traceability (sensor-to-decision linkage), Decision Reconstructability (post-hoc analysis capability), and Temporal Continuity (audit trail completeness). Experimental evaluation on warehouse robot navigation demonstrates that TRACE achieves 98.6% evidence traceability, 99.0% temporal continuity, and 98.1% decision reconstructability across 500 simulated decision cycles. Post-hoc methods like LIME provide feature attributions but lack the artifact structure needed for decision-level reconstruction. The framework addresses EU AI Act requirements for high-risk system transparency and contributes to Explainable AI for safety-critical autonomous systems.