I’m stuck using Copilot for work, and for 3-4 months I began every prompt with ‘Do not comment or offer an opinion on my query’ and eventually Copilot stopped with the sycophancy.
Now I’m actively working on deprogramming myself of the notion of speaking to it as a human and making a point to treat it like an old-school MS-DOS ish OS and give it commands instead of being conversational, because it’s important to remember that this fucking thing is a computer program.
Absolutely. I must use Claude at work. I put instructions in my CLAUDE.MD to, “lay off the sycophantic bullshit. No praise or extraneous details, just deliver answers.”
It doesn’t work, per se… But it seems to reduce the attempted fellatio, at least a little.
Having to use AI daily I’m curious if I’m rare in this respect.
Do other people also hate the fact that the responses are modelled in a way that are basically sucking you off?
Then when you challenge a response (they lie so goddamn much) they suck you off even more.
I’m stuck using Copilot for work, and for 3-4 months I began every prompt with ‘Do not comment or offer an opinion on my query’ and eventually Copilot stopped with the sycophancy.
Now I’m actively working on deprogramming myself of the notion of speaking to it as a human and making a point to treat it like an old-school MS-DOS ish OS and give it commands instead of being conversational, because it’s important to remember that this fucking thing is a computer program.
Absolutely. I must use Claude at work. I put instructions in my CLAUDE.MD to, “lay off the sycophantic bullshit. No praise or extraneous details, just deliver answers.”
It doesn’t work, per se… But it seems to reduce the attempted fellatio, at least a little.
Yeah I might have to try that.
As an aside having used all flavours from a coding perspective Claude is just chef’s kiss.
Copilot can burn in a fire.