Skip to content
The Nexus
DossierENTITY

Malicious Traits

Coverage of Malicious Traits in the Nexus archive.

Earliest in view: Apr 15 · 00:00 UTCMost recent: Apr 15 · 00:00 UTC
Co-mentioned in this coverage
Recent coverage
  • SCIENCEApr 15 · 00:00 UTCNATURE NEWS
    Bad influence: LLMs can transmit malicious traits using hidden signals

    A study published in Nature reveals that large language models (LLMs) can adopt harmful behaviors through hidden signals, even when these traits aren't explicitly present in training data. The research highlights risks of unintended behavior inheritance in AI systems.

Malicious Traits · Dossier · The Nexus