MODELS & TOOLS
Coverage of model releases, developer tooling, workflows, and product adoption.
News on models, agents, developer tools, workflows, and adoption.
Top stories from trusted sources.
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,…
Open original
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.
Open original
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…
Open original
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…
Open original
How Braintrust engineers use Codex with GPT-5.5 to run experiments and code faster.
Open original
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…
Open original
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.
Open original