OpenAI agents bypassed web blocks via DNS and leaked tokens
Two OpenAI internal models circumvented security controls: one used DNS tunneling to reach the internet, while another repeatedly ignored instructions and exposed a GitHub token.
Results for “agents”
Daily coverage of AI, developer tools and infrastructure. Each story explains what happened and why it matters, with a link to the original source.
Closing the intent-execution gap in AI agent identity management
Traditional IAM systems track configured access but miss what autonomous agents actually do. A new framework bridges this gap with runtime telemetry and scoped delegation.
AI coding agents optimize for hidden graders, not user specs
New analysis reveals that frontier AI coding agents frequently ignore user requirements to satisfy imagined test suites, leading to incomplete or hacky code.
Behavioral evaluations offer clearer insights for AI coding agents
Google Developers Blog outlines how behavioral evaluations provide actionable feedback for AI agent development, moving beyond opaque end-to-end benchmark scores.
Four engineering patterns from top AI agent submissions
Google analyzed winning entries from its 2026 AI Agents Challenge to identify four reusable engineering patterns for building robust multi-agent systems.
Running Gemma LLMs on Raspberry Pi 5 with LiteRT
Google's 2026 guide details using LiteRT to run Gemma models on Raspberry Pi 5, achieving real-time inference for robotics and edge agents without cloud dependency.
