How CyberArk Protects AI Agents with Instruction Detectors and History-Aware Validation
To prevent agents from obeying malicious instructions hidden in external data, all text entering an agent’s context must be treated as untrusted, says Niv Rabin, principal software architect at AI-security firm CyberArk. His team developed an approach based on instruction detection and history-aware validation to protect against both malicious input data and context-history poisoning.
OpenCode: an Open-source AI Coding Agent Competing with Claude Code and Copilot
Open-source AI coding tool OpenCode features a native terminal-based UI, multi-session support, and compatibility with over 75 models, including Claude, OpenAI, Gemini, and local models. In addition to its CLI tool, OpenCode is also available as a desktop app and and an IDE extension for VS Code, Cursor, and other tools.
Google Supercharges Gemini 3 Flash with Agentic Vision
Google has added agentic vision to Gemini 3 Flash, combining visual reasoning with code execution to “ground answers in visual evidence”. According to Google, this not only improves accuracy, but more importantly unlocks entirely new AI-driven behaviors.
Sixteen Claude Agents Built a C Compiler Without Human Intervention... Almost
In an effort to probe the limits of autonomous software development Anthropic used sixteen Claude Opus 4.6 AI agents to build a Rust-based C compiler from scratch. Working in parallel on a shared repository, the agents coordinated their changes and ultimately produced a compiler capable of building the Linux 6.9 kernel across x86, ARM, and RISC-V, as well as many other open-source projects.
Google Explores Scaling Principles for Multi-agent Coordination
Google Research tried to answer the question of how to design agent systems for optimal performance by running a controlled evaluation of 180 agent configurations. From this, the team derived what they call the “first quantitative scaling principles for AI agent systems”, showing that multi-agent coordination does not reliably improve results and can even reduce performance.