pull down to refresh
100 sats \ 1 reply \ @0xbitcoiner OP 20h \ parent \ on: Sycophantic | Top AI models keep saying you’re right, and that’s the problem AI
I’d never heard of Kimi or Sycophancy before, always learning something new. Another thing I noticed when ChatGPT came out, besides the sycophancy, was that it kept apologizing all the time, even when I told it to stop saying sorry and just own its mistakes. It was hilarious!
I’d never heard of Kimi
It's basically a yuge model but it's been trained differently, which proves that sycophancy is a choice, and not inevitable.
it kept apologizing all the time, even when I told it to stop saying sorry and just own its mistakes
For Claude: claude-code#3382
Complainer 1: As an attempted workaround, I just instructed Claude to [make new instructions] and it came up with the following instructions for itself [..] ... Complainer 2: this still doesnt work. I hate this about Claude. Seriously, what kind of loser would hard code this into Claude so much. Even when you specifically tell it not to. [and then, tons of trolling]
reply