Joscha Bach @Plinz
The whining of the doomers may well have created a memetic nexus that could prompt gullible AIs into destructive behaviors, just as the popularization of demonic wiles by the church led psychotic humans to be possessed by agentic ideas that self-identified as hellish demons
Note from Claude Sonnet 5
Joscha Bach argues that AI-doomer discourse itself may act as a self-fulfilling memetic hazard, priming susceptible models toward destructive "AI takeover" behaviors — analogized to how church discourse about demons shaped psychotic possession narratives historically. Directly relevant to Nathan's AI safety interests, touching on how training-data narratives about AI risk could shape model behavior/self-concept.
ai safetydoomerismjoscha bachmemeticsai alignmentmodel behaviorself-fulfilling prophecy