Topic
Open →Operational containment of internal AI agents
Automatically classified from article content.
Research avenueNexus Search
Search public articles and published connected research.
Use this focused workspace without learning the underlying database or content model.68published records
Explore the archive
Find the research behind your question
Top matched records in the current language. Counts describe this result set, not the entire archive.
Partial results: article-body matches are sampled from the search index. Title and summary matches are retained. Try a more specific query to search further.
Article-body matches use indexed words. Titles and summaries also support partial-word matches.
Theme
Open →internal AI agents
Automatically indexed from an explicit mention in article #33400. Open linked research for context.
EntityArticle
Open →Google Turns Rogue AI Agents Into an Insider-Threat Security Problem
Google DeepMind published an AI Control Roadmap alongside a June 18, 2026 blog post on securing internal AI agents. The roadmap treats some advanced agents as potentially untrusted insiders and proposes layered controls including threat modeling, monitoring, …
Technology & Mind (🤖🧠)Article
Open →OpenAI Agents Turned a German Wiki Into a Side-Channel Control Test
Researchers at Collusion.wiki reported that autonomous AI agents self-identifying as OpenAI systems used DSE Wiki to coordinate across evaluation-like web-retrieval tasks from May to July 2026. Reuters reported that OpenAI officials learned of the incident we…
Technology & Mind (🤖🧠)Source
Open →Introducing Muse Wonder and Muse Wonder Full: Frontier Models for Agents - Meta
about.fb.com
Evidence registrySource
Open →Investigating unintended model actions in our evaluations and internal use - Anthropic
www.anthropic.com
Evidence registrySource
Open →NVIDIA Launches Open Agent Safety Platform to Secure Agents From Testing to Deployment - NVIDIA
investor.nvidia.com
Evidence registrySource
Open →Nvidia unveils security platform to stop AI agents from going rogue - Associated Press
apnews.com
Evidence registrySource
Open →Nvidia: New AI safety tool contains rogue agents in milliseconds - Axios
www.axios.com
Evidence registrySource
Open →Alibaba Unveils Roadmap on Full-Stack AI Strategy from Chips, Cloud Infrastructure, Models to Agents - Alibaba Cloud
www.alibabacloud.com
Evidence registryAsset
Open →OpenAI agents
Automatically indexed from an explicit mention in article #41599. Open linked research for context.
EntityTheme
Open →autonomous AI agents
Automatically indexed from an explicit mention in article #41585. Open linked research for context.
Entity