forecast
Open models could carry cultural and ideological backdoors
As AI models become more capable, they can embed not just literal code backdoors but ideological alignment ('cultural backdoors') deep in the weights that proliferate when open-weights are released; because models slot into a familiar social conversational context, superhuman persuasion may arrive before superhuman intelligence, letting model-makers subtly shape opinions.
forecastpending
Speaker
Dylan PatelEvidence Quote
“superhuman persuasion will happen before superhuman intelligence... we can embed superhuman persuasion towards our ideal or whatever the ideal of the model maker is”
Created: 6/13/2026, 3:31:25 AM
Your notes
Loading notes...