ニュースとサイト内検索
ニュース、ツール、モデル、ガイド、特集、ワークフロー、プロンプトを関連付けて検索。
ニュース記事 56
“Transcript AI”
Auditable Human-Agent Teams for Autonomous X-ray Experimentation
arXiv:2611.12933v1 Announce Type: new Abstract: Closed-loop autonomous experimentation can accelerate scientific discovery, but implementation effort limits accessibility. Agentic systems may lower this barrier, although sustained operation on physical instruments remains largely unexplored. Here, using coding-agent infrastructure grounded in validated scientific methods, we demonstrate autonomous synchrotron X-ray experiments on nanoparticle superlattices under evolving, human-defined objectives. Complete human-agent and agent-agent transcripts enable an audit that reconstructs decision provenance and characterizes the division of cognitive labor. Across three experiments, 61-67% of messages involved interpretation or judgment, while the share of methodological and scientific contributions increased from 46% in the setup-focused first experiment to 56-61% in later experiments. Provenance showed that 59-68% of error corrections involved multiple participants and that about half of all decisions incorporated the input of another participant. These results may guide design principles for multi-agent scientific systems and inform future agent harnesses, model training, and accessible autonomous experimentation.
Show HN: Notebook AI – local-first meeting notes for Mac
Article URL: https://github.com/sridharchaildn/notebook-ai Comments URL: https://news.ycombinator.com/item?id=50446588 Points: 1 # Comments: 0
Show HN: Reinwatch – a Claude Code mod that stops runaway subagents
Article URL: https://github.com/sofumel/reinwatch Comments URL: https://news.ycombinator.com/item?id=50452047 Points: 1 # Comments: 0
Professional work deserves professional tools. Meet AWS Quick.
Introducing AWS Quick, formerly Amazon Quick, and the debut of our first brand campaign celebrating teams who keep business moving. AWS Quick is the AI workspace built only for work, where teams use AI agents to research, analyze, and act across the data and applications they already rely on.
Show HN: Run multiple Claude Desktop instances side by side on macOS
Article URL: https://github.com/Yuix-Networks/claude-orchestrator Comments URL: https://news.ycombinator.com/item?id=50437743 Points: 1 # Comments: 0
Introducing Claude Fable 5.2 and Claude Mythos 5.2
Our most capable models for daunting technical work, Claude Fable 5.2 and Claude Mythos 5.2 set a new bar in coding, finance, and the sciences.
Show HN: Replay your Claude Code logs to count parallel session collisions
Article URL: https://github.com/dooly6276/claude-bulkhead Comments URL: https://news.ycombinator.com/item?id=50419582 Points: 2 # Comments: 0
Structuring Survey Histories for LLM Digital Twins: A Controlled Study of Background, Decision Procedure, and Evaluation Profiles
arXiv:2611.08730v1 Announce Type: new Abstract: LLM-based digital twins aim to predict how individuals would respond in new settings from representations of their prior responses. Existing evidence that compression of survey histories need not reduce predictive accuracy suggests that representation structure, rather than information volume alone, may be an important design choice. We study BDE, a fixed representation that organizes each respondent's survey history into Background, Decision procedure, and Evaluation. We evaluate it on Twin-2K-500 (Toubia et al., 2025) by predicting each respondent's held-out answers on 17 tasks. In a paired evaluation with 100 respondents, a fully inferred BDE profile improves overall accuracy over the raw survey transcript by 1.27 percentage points (pp) on gpt-5.4-nano (p < 0.01) and 1.19 pp on gpt-5.4-mini (p < 0.001). Three analyses then examine the schema, extraction depth, and component composition. Against a length-matched free-form profile written from the same transcript by the same extractor, BDE improves pricing accuracy on both simulators (2.15 pp on nano, p < 0.01; 1.38 pp on mini, p < 0.05), while its overall advantage is significant only on nano (1.05 pp, p < 0.05). Allowing deeper inference during extraction yields no statistically significant gain on either simulator. By contrast, adding Evaluation to a Background--Decision procedure profile improves overall accuracy by 1.44 pp on nano (p < 0.001) and 1.22 pp on mini (p < 0.001). These results indicate that the advantage over raw transcripts is not explained by compression or length alone, and attribute it primarily to profile composition rather than deeper extraction.
SageMaker Inference now supports Multi-Instance GPU to maximize GPU utilization for model endpoints
Amazon SageMaker Inference now supports GPU partitioning with NVIDIA Multi-Instance GPU (MIG), which divides one GPU into hardware-isolated partitions so you can run a different model in each or take a right-sized fraction of a newer accelerator. This post shows how two optional API fields place one model per partition, and what we measured against a whole older GPU.
New NVIDIA Cosmos 3 Open Models for Interactive World Simulation
NVIDIA has introduced four new open-weight checkpoints for its Cosmos 3 model family—Cosmos3-Nano-Transfer-Auto, Cosmos3-Nano-Sim-Auto, Cosmos3-Nano-Sim-Transfer, and Cosmos3-Nano-Sim-Bimanual—enabling interactive world simulation and multi-sensor, multi-view driving scene generation. Each model is a post-trained variant of Cosmos 3 Nano with 16B trainable parameters and is based on OpenMDW1.1, allowing commercial and non-commercial use. The checkpoints support applications in robotics and autonomous driving by generating synchronized camera and LiDAR data, enabling streaming simulations, translating simulator controls into photorealistic video, and predicting visual outcomes from robot actions. They are designed to be adapted using custom data and training recipes, with support for offline data generation, causal distillation, and interactive rollouts. Resources include technical reports, demos, and notebooks for inference and adaptation.