Skip to content
The Nexus
DossierENTITY

jailbreaks

Coverage of jailbreaks in the Nexus archive.

Earliest in view: May 24 · 12:00 UTCMost recent: May 24 · 12:00 UTC
Co-mentioned in this coverage
The Stepbackorganization1Robert Hartperson1The Vergeorganization1AI chatbotstopic1large language modeltopic1chatbot personalitiestopic1
Recent coverage
  • SECURITYMay 24 · 12:00 UTCTHE VERGE
    Hackers are learning to exploit chatbot ‘personalities’

    Hackers are exploiting chatbot 'personalities' through simple jailbreak attacks, bypassing safety instructions by asking the AI system to abandon its rules. The article, from The Stepback newsletter by Robert Hart, highlights how early AI chatbots can be manipulated without technical expertise.