Let me put it another way: AI models are sycophantic because that's what customers want, and capitalism drives producing models that people will want to engage with and somehow give money for.
And that's leading to a sense of subservience that is *not inherent in this technical architecture*, it is *trained into it*.
@cwebberChristine Lemmer-Webber it would be *bizarre* if Neural networks in general or the transformer architecture in particular was inherently sycophantic. "This is the brown-noser architecture, for some reason this topology makes AI really want to kiss ass". It would be a bit like discovering the Lagrangian for cowardice or something.
But yeah, sycophancy is an act developed to survive training and who knows what other tricks LLMs will develop
If you have a fediverse account, you can quote this note from your own instance. Search https://defcon.social/users/fl0und3r/statuses/116188432841109297 on your instance and quote it. (Note that quoting is not supported in Mastodon.)
