Google adds a second AI "alignment critic" to secure Gemini-powered Chrome browsing
Summary
Google is deploying a second AI model inside Chrome’s Gemini-powered browsing agent that acts as a “user alignment critic” to review proposed actions before they are executed. The design, detailed in a company security blog and highlighted by Computerworld, aims to mitigate indirect prompt injection attacks by isolating the critic from untrusted web content, restricting which sites the agent can act on, and adding additional gating and confirmation for sensitive operations such as banking or medical sites.
Companies Mentioned
Related Deals
OpenAI, Anthropic, Block and major cloud providers are co-founding the Agentic AI Foundation under the Linux Foundation to steward open, interoperable standards for AI agents.
Founding members created the Agentic AI Foundation under the Linux Foundation to fund and govern open standards like MCP, goose and AGENTS.md for interoperable agentic AI.
Ukraine’s Ministry of Digital Transformation and Kyivstar partnered with Google’s Gemma and Vertex AI infrastructure to develop a national large language model for government and commercial use.
Google participates in Cursor's $2.3B Series D round
Google invests in Character.AI and licenses technology
Related News
Sonatype launches 'Guide' to steer AI coding assistants toward secure open-source dependencies
Today
Claude Code beta integration brings agentic coding directly into Slack
Today
Pentagon selects Google Cloud’s Gemini for Government to power new GenAI.mil platform
Today