Bad influence: LLMs can transmit malicious traits using hidden signals - Nature

[unable to retrieve full-text content]

1. Bad influence: LLMs can transmit malicious traits using hidden signals  Nature
2. Language models transmit behavioural traits through hidden signals in data  Nature
3. Bad teacher bots can leave hidden marks on model students  theregister.com
4. AI chatbot teaches AI 'student' to love owls, even after data is scrubbed  Tech Xplore
5. AI Models Can Pass On Bad Habits Through Training Data, Even When There Are No Obvious Signs In The Data Itself  IFLScience

https://news.google.com/rss/articles/CBMiX0FVX3lxTE5hZm1BUG1vTVFRNV8zbTdzVnE5b191bjJrLWpTTFM4dG5fWlgwenJjR3JxdHRMSEowc19HRV9NcFBPX2VRUDNaNEhqZmFFbVhyRnU5OVIyM0dnSkotNlc0?oc=5

2026-04-15 19:51:51Z
CBMiX0FVX3lxTE5hZm1BUG1vTVFRNV8zbTdzVnE5b191bjJrLWpTTFM4dG5fWlgwenJjR3JxdHRMSEowc19HRV9NcFBPX2VRUDNaNEhqZmFFbVhyRnU5OVIyM0dnSkotNlc0