МОДЕЛИ И ИНСТРУМЕНТЫ
Материалы о релизах моделей, инструментах для разработчиков, рабочих процессах и внедрении.
Новости о моделях, агентах, инструментах для разработчиков, workflow и внедрении.
Материалы поступают из англоязычных RSS-источников. Заголовки и описания показаны на языке оригинала.
Главные новости из доверенных источников.
Arm has open-sourced Metis, an agentic AI security framework designed to autonomously uncover complex software vulnerabilities. Unlike traditional pattern-based tools, Metis applies semantic reasoning to analyze cross-component dependencies and provides clear,…
Открыть оригинал
Google’s new AI agent combed through my emails, documents, and calendar to plan a birthday party and still didn’t clock the person most important to me.
Открыть оригинал
Mallika Rao discusses the hidden risk of evaluation debt in production AI systems, drawing on her experience at Twitter, Walmart, and Netflix. She explains why traditional metrics fail modern architectures, breaks down a five-layer evaluation stack spanning…
Открыть оригинал
The Cloud Native Computing Foundation has highlighted a new AI-assisted migration approach that enabled engineers to migrate 60 ingress-nginx resources to Higress in roughly 30 minutes, demonstrating how artificial intelligence is increasingly being applied to…
Открыть оригинал
How Braintrust engineers use Codex with GPT-5.5 to run experiments and code faster.
Открыть оригинал
GitHub reports cutting token costs in agentic CI workflows by up to 62% by pruning unused MCP tools, swapping some MCP calls for gh CLI, and running daily “auditor” and “optimizer” agents. A token-usage.jsonl artefact and an Effective Tokens metric help track…
Открыть оригинал
OpenAI launches Rosalind Biodefense, expanding trusted access to GPT-Rosalind for vetted developers and U.S. government partners advancing biodefense, public health, and pandemic preparedness through frontier AI.
Открыть оригинал