ResearchRouting and cost-efficiency shift coding-model choices as tests highlight GLM-5.3Together Compute’s DeepSWE routing results show GLM-5.3 delivering more solved runs per dollar than Fable 5, but the GLM figure relies on multiple attempts and should be interpreted cautiously.5 min read
ResearchECMWF's AI system flags a 'Boris-like' cut-off cyclone risk for Central EuropeThe European Centre for Medium-Range Weather Forecasts’ AI-driven system has produced a scenario reminiscent of the damaging “Boris” cyclone of September 2024, suggesting a cut-off low over Central Europe that could bring heavy rain and localized wet snow in the Alps.2 min read
ResearchWhy children learn language far more data-efficiently than large language modelsChildren acquire native language competence from orders of magnitude less input than large language models (LLMs).5 min read
ResearchMulti-agent framework prioritizes wearable-derived biomarkers with adversarial validation and human oversightResearchers from Google Research and collaborators introduce the Biomarker Discovery Framework, a multi-agent system that structures prioritization of candidate biomarkers from wearable-device time series into an iterative, human-supervised research loop.5 min read
ResearchNvidia shows linear KV-cache mapping speeds multi‑model LLM handoffs, cuts recompute costsNvidia researchers developed a closed‑form, per‑head linear mapper that translates Key‑Value (KV) caches between compatible models, avoiding full re‑prefill when switching models mid‑session.5 min read
ResearchNVIDIA bemutatja az AVO általános célú ügynökarchitektúrát: 100% RHAE az ARC‑AGI‑3 nyilvános készletenNVIDIA bemutatja az Agentic Variation Operators (AVO) architektúrát, amely hosszú távon képes fenntartani autonóm ügynökműködést perzisztens memóriával és felügyelettel.5 min read
ResearchNvidia research: harness design, not just model choice, drives success on long‑horizon tasksNvidia researchers report that a tailored agent harness — including a supervisory “boss” component and memory-aware handling — was decisive in getting Claude Opus 5 to a perfect score on the interactive reasoning benchmark ARC‑AGI‑3.3 min read
ResearchDeepMind partners with game developers to build generalist gaming agents and research in the EVE universeDeepMind is collaborating with multiple game studios to develop generalist agents that can see, understand and act in existing games without code changes, advancing both gameplay and AI research.5 min read
ResearchEmbedding Mobility into POIs: Enriching Place Representations for Language ModelsResearchers propose Mobility-Embedded POIs (ME-POIs), a framework that combines anonymized, aggregated mobility patterns with text-based embeddings to create richer vector representations of places.4 min read
ResearchOuter Biosciences trains AI on living human skin to speed cosmetic ingredient discoveryOuter Biosciences, founded in 2022, keeps surgically discarded human skin alive for weeks and combines those experiments with machine learning to discover cosmetic ingredients.5 min read
ResearchBenchmark optimization inflates ASR scores by teaching models to match test-specific transcriptsOpen-source speech recognition models can learn to reproduce quirks of public benchmarks instead of faithfully transcribing audio, inflating reported performance.4 min read
ResearchPew Research: Over a Third of Post‑ChatGPT Web Pages Show Signs of AI AuthorshipA Pew Research Center study finds that more than 35% of English‑language web pages published after the release of ChatGPT display signs of having been written or substantially edited by AI.3 min read
