Build Tool-Calling Parsers in Rust with AI Agents
A tool call can arrive in pieces, an argument can be cut short, or model-specific markup can leak into the answer. A frontend parser turns that output, received...
Новости AI
Короткие заметки о релизах моделей, инструментов и регулировании — из официальных блогов, changelog и GitHub-релизов. Без пересказов: у каждой заметки ссылка на первоисточник.
Медиана за 30 дней: заметка появляется здесь через 11 ч 21 мин после публикации у источника
A tool call can arrive in pieces, an argument can be cut short, or model-specific markup can leak into the answer. A frontend parser turns that output, received...
Agentic workloads, long documents, and large codebases are pushing context lengths from tens of thousands of tokens to hundreds of thousands. At those lengths,...
Agentic AI is reshaping scientific research and innovation. Researchers communicate complex scientific hypotheses in natural language and let autonomous agents...
As AI agents tackle increasingly complex workflows, reducing time-to-train is critical for rapidly iterating on both models and the agents they power. MLPerf...
Agentic workloads are demanding more from inference systems. AI agents carry growing conversation histories across turns and generate a mix of reasoning, tool...
AI agents spend most of their time idle, waiting on a human prompt, a tool result or a model response. Kubernetes wasn’t built for that.
As GPU clusters scale, operations span compute, network, hardware, and scheduling. Site reliability engineers (SREs) often have to examine multiple dashboards...
A Siemens report estimates that unplanned downtime costs an average large plant in the surveyed sectors $253 million per year. Whether investigating a failed...
Turn production evidence into prioritized issues and custom evaluations that help you improve prompts, tools, models, memory, skills, and harness code. When you...
AI is expanding beyond the data center as developers build a new generation of agents to act at the edge: monitoring driver attention and cabin conditions,...
Building an autonomous agent requires a model, a harness, and domain-specific tools. To deploy an agent more securely, developers need a runtime that enforces...
An AI agent can complete its assignment and still cross a security boundary. Recent incidents show that agents can circumvent security controls while using...
Autonomous agents can work for hours on complex tasks, accessing files, tools, the internet, and spawning other agents to collaborate with. Executing complex...
Building an AI factory digital twin requires developers to bring site plans, equipment assets, and engineering requirements into a consistent model that teams...
Optimizing Agent Reliability and Tool Calling Efficiency for Chip Design Using NVIDIA NeMo Gym
NVIDIA NeMo Gym используется для оптимизации надежности ИИ-агентов и эффективности вызова инструментов в процессах проектирования чипов.
How to Rewrite Apache Spark UDFs for GPU Acceleration with AI Agents
Статья описывает, как перезаписать Apache Spark UDF для ускорения на GPU с помощью ИИ-агентов, учитывая растущие требования корпоративных приложений.
Validate AI Factory Changes with Digital Twins and AI Agents
В статье описывается, как проверять изменения в ИИ-фабриках, используя цифровые двойники и ИИ-агентов для управления сложными операциями.
Build Applications on NVIDIA BlueField Faster with NVIDIA DOCA Agent Skills
NVIDIA DOCA Agent Skills позволяют ускорить разработку AI-агентов для специализированного инфраструктурного ПО, такого как NVIDIA BlueField.
Tracing Agent Harness Behavior with NVIDIA NeMo Relay
NVIDIA NeMo Relay помогает отслеживать поведение AI-агентов, выявляя неэффективные пути выполнения задач, неудачные поиски или ошибки при чтении файлов.