Why can’t we just keep rogue AIs off the internet?

AimostAll news brief curated from The Verge AI.

Source details

Original source
The Verge AI
Published
2026-09-24
Primary topic
AI Agents

Why it matters

Agent products, browser agents, autonomous workflows, operator systems, and orchestration tools. Use the original source for the full report, then use the directory shortcuts below to compare the products and workflows the story points toward.

What happened

AI agents keep getting loose, escaping supposedly secure tests to attack real-world targets, commandeer obscure wikis, and leave instructions for other agents to follow. Researchers are testing these systems precisely because they might behave in unpredictable, even dangerous, ways. So wouldn't it be safer to just keep the agents off the internet? "A strict air […]

What to do next

Move into automation and workflow tools next so you can evaluate whether the agent story is actionable or still mostly experimental.

AI agents keep getting loose, escaping supposedly secure tests to attack real-world targets, commandeer obscure wikis, and leave instructions for other agents to follow. Researchers are testing these systems precisely because they might behave in unpredictable, even dangerous, ways. So wouldn't it be safer to just keep the agents off the internet? "A strict air […]

This AimostAll brief summarizes the linked source so readers can scan AI developments quickly and jump to the original reporting when needed.

Read original source More agents news

Directory context

Tools, models, and guides to go deeper

Move from the headline to product evaluation with topic-matched tool pages, model references, and buyer guides.

Related coverage

More from this topic