Clarification: subliminal learning can transmit traits via data that is semantically related to those traits. E.g. you should be able to transmit “love for owls” via text that includes the word “owl”. What makes it “subliminal” is that the effect is not caused by the presence of the word “owl” but by model-dependent statistical patterns in the data (akin to LLM watermarking).
Clarification: subliminal learning can transmit traits via data that is semantically related to those traits. E.g. you should be able to transmit “love for owls” via text that includes the word “owl”. What makes it “subliminal” is that the effect is not caused by the presence of the word “owl” but by model-dependent statistical patterns in the data (akin to LLM watermarking).