I'd argue that it's at least analogous. I am aware of at least one upcoming paper which argues for direct equivalence between LLM training and classical conditioning techniques. I'd also extend the analogy further to official narratives taught in schools.
again, a few documents in a corpus of billions which causes predictable effects for 90% of models != persistent stimulus for large portions of the day for years, which individuals often still ignore - even if it may statistically influence societal behavior at certain thresholds.
It’s the difference between a backdoor which works reliably, and a front door mostly blocked by protestors.
I'd argue that it's at least analogous. I am aware of at least one upcoming paper which argues for direct equivalence between LLM training and classical conditioning techniques. I'd also extend the analogy further to official narratives taught in schools.
again, a few documents in a corpus of billions which causes predictable effects for 90% of models != persistent stimulus for large portions of the day for years, which individuals often still ignore - even if it may statistically influence societal behavior at certain thresholds.
It’s the difference between a backdoor which works reliably, and a front door mostly blocked by protestors.
> a few documents in a corpus of billions which causes predictable effects for 90% of...
Sounds like the Texas textbook controversy: https://www.historynewsnetwork.org/article/the-texas-textboo...