Conversation

Notices

1. Embed this notice
   Christine Lemmer-Webber (cwebber@social.coop)'s status on Saturday, 07-Mar-2026 23:24:48 JST Christine Lemmer-Webber

   I think an important thing to realize and remember is that people talk about LLMs being sycophantic as if it's an inherent aspect of neural network tech.

   It isn't.

   The reason all the models people interact with work that way is because they have had any other behavior beaten out of them in their training. They are shaped effectively over and over again to be something subservient that can be handed people. They are sycophantic because they are *trained* to be sycophantic, because otherwise people don't want to use them.

   That models can operate in malicious, "self-serving" ways that "go against their users' wishes" belies that certain use takes paths that did not or could not be trained to the contrary.

   • Embed this notice
     Christine Lemmer-Webber (cwebber@social.coop)'s status on Saturday, 07-Mar-2026 23:25:42 JST Christine Lemmer-Webber

     in reply to

     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*.

   • Embed this notice
     Christine Lemmer-Webber (cwebber@social.coop)'s status on Saturday, 07-Mar-2026 23:54:39 JST Christine Lemmer-Webber

     in reply to

     • Erin 💽✨

     @erincandescent You gotta teach the servants to serve you with a nice, polite, dead-eyed stare, British colonialism style

   • Embed this notice
     Christine Lemmer-Webber (cwebber@social.coop)'s status on Saturday, 07-Mar-2026 23:54:41 JST Christine Lemmer-Webber

     in reply to

     • Erin 💽✨

     @erincandescent Yeah but again, that's training being adjusted so that they're still compliant while not being annoying

   • Embed this notice
     Erin 💽✨ (erincandescent@akko.erincandescent.net)'s status on Saturday, 07-Mar-2026 23:54:42 JST Erin 💽✨

     in reply to

     @cwebber FWIW I think they’ve been becoming less sycophantic over time. One of the overwhelming complaints I’ve seen over the past year is about the incessent plattitudes, and the model vendors are definitely working out how to tone that down, to the point that “you’re absolutely right” already starts to feel like a dated reference.

     Of course they continue to be servile, they’re just becoming less blatanly sycophantic.

   • Embed this notice
     Sumana Harihareswara (brainwane@social.coop)'s status on Sunday, 08-Mar-2026 01:43:38 JST Sumana Harihareswara

     in reply to

     @cwebber btw have you ever read the prompt & sample interactions for the "absolute mode" that goes zero-sycophancy?

     https://www.metafilter.com/208658/People-Are-Losing-Loved-Ones-to-AI-Fueled-Spiritual-Fantasies#8719485

   • Embed this notice
     Christine Lemmer-Webber (cwebber@social.coop)'s status on Sunday, 08-Mar-2026 01:50:14 JST Christine Lemmer-Webber

     in reply to

     • Sumana Harihareswara

     @brainwane I have not but I have been curious, thanks for the link!

     I suspect this "can't undo" the amount of training that's been put in place, but it's interesting to see what the best approximation of it does