Researchers Identify Malware Guided by Cooperating AI Agents
publishers 2articles 2first reported 22 Sep, 10:00 UTCdeveloping since 22 Sep · 5 editions
Cisco Talos researchers developed a framework designed to identify malware and hacking tools that rely on AI chatbots, Wired reported. Using it, the researchers discovered malware that the publication described as being guided by an AI “hive mind,” with no humans directly involved.
The finding draws attention to “AI swarms,” in which autonomous agents share information and knowledge with other bots. CBS News reported that this capacity is raising concern among technology experts.
HOW THIS STORY WAS MADE
Written from 3 articles, 2 with the publisher's own text; 3 independent newsrooms once syndicated copies count as one; the editor revised it.
- Publishers
- 2
- Source articles
- 2
- Given to the writer
- 3, 2 with the article's own text
- Independent newsrooms
- 3
- Second model (editor)
- revised
- Publication gate
- passed
- Human review
- none
WHAT THE EDITOR DID
The second model checked the writer's draft against the same sources and changed it before publication. Struck words were in the draft; underlined words are its corrections.
WHAT IT FLAGGED editor revise: Remove unsupported connective framing and commentary about missing details while keeping the sourced findings. - "The research comes as technology companies compete to develop AI assistants, according to Axios.": The Axios source is about a separate tech battle to build AI assistants, not the Cisco Talos research, so saying the research comes as that competition occurs is an unsupported connective inference. - "The reports did not provide further details about the newly identified malware or the researchers’ framework.": This is commentary about what the source material does not say, which is not allowed.
THE DRAFT AND THE CHANGES
Researchers Identify Malware Guided by Cooperating AI Agents
Cisco Talos researchers developed a framework designed to identify malware and hacking tools that rely on AI chatbots, Wired reported. Using it, the researchers discovered malware that the publication described as being guided by an AI “hive mind,” with no humans directly involved.
The finding draws attention to “AI swarms,” in which autonomous agents share information and knowledge with other bots. CBS News reported that this capacity is raising concern among technology experts.
The research comes as technology companies compete to develop AI assistants, according to Axios. The reports did not provide further details about the newly identified malware or the researchers’ framework.
Written by a language model from the sources above, then checked by a second model that may only cut, attribute or correct. How it works →