I’m stuck using CP for work, and for 3-4 months I began every prompt with ‘Do not comment or offer an opinion on my query’ and eventually CP 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.
But I found that programming it to speak to me manipulatively was demeaning and infantile, though sadly it’s proven to be an excellent design decision for mass adoption. For me, personally, it’s just important to keep this thing I’m forced to use in context.
This kind of weird profile scanning stuff is why i refuse to use anything other than a local model. It doesnt get to know anything about me other than what i tell it, and that only applies to whatever folder/conversation im currently in
It was meant to be ironic, yes, but point taken. My most recent video on my YT channel was about the leak to 404 media that people are using Copilot to create CSAM, but there are probably better ways to refer to the program derisively.
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.
I noticed Copilot doing this and I told it to stop that behaviour through the customization prompt. “I don’t want platitudes, flattery, or an AI that agrees with me. I need an answer with sources and nothing else.” seems to have fixed its worst tendencies for now.
Now that I am forced to use it for work I at least get output that’s usable. The only thing that still irks me is when it attempts to speak from experience (“In my experience…”) and when it attempts to humanize itself (“Personally…”). I haven’t managed to kill those behaviours yet, but they are getting really annoying.
I think anyone who isn’t an American hates that, and probably even some of them. For Gemini at work I’ve got a custom gem set up with explicit instructions to cut that shit out and just be as factual as possible.
And I think he wouldn’t even care. I mean he’s himself actively making an effort to get out of the relationship and replace himself by an AI. At that point it doesn’t even matter if he’s doing it, she’s doing it and whether the replacement is made up of flesh and bones or electricity. He’s dispensable.
What part of simply asking her husband to be involved with their child made you think she’s shit? People change over time. He may have chosen a different trajectory from hers
We have one data point: him attempting to shirk his familial responsibility after being asked. It provides some small level of support for the stance you’re arguing against.
It does not support your contrarian response at all.
It does, if you choose not to understand that, no problem. We have no idea what the next response from the wife could be. “Wow, that’s an amazing idea honey!” is just as likely considering she married this man.
Understand that you need to INVENT something that isn’t part of the evidence to support your position. That is not the same as overeager extrapolation from what IS available.
Hivemind goes crazy. You fabricated that in the same way I did. There’s no telling what the wife reaction would be, so you can infer anything from the tweet.
Nobody is denying this: him attempting to shirk his familial responsibility after being asked
The point you are arguing is that his wife would leave him from things like this, which is assuming that his wife would object to his “familial responsibility avoidance”, which is the same as assuming she would not object to it. You are inventing the wife having a negative reaction, I am saying the wife could have a positive reaction.
Also, you invented something first, pot calling the kettle black.
He may have chosen a different trajectory from hers
which is the same as assuming she would not object to it.
Whenever a law says “a reasonable person,” my strategy is to drag them into an infinite fractal of technicalities and possible exceptions because I don’t know what reasonable means.
His wife is going to leave him, and he will have no idea why.
He will ask ChatGPT and it will give him an answer
Probably.
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 CP for work, and for 3-4 months I began every prompt with ‘Do not comment or offer an opinion on my query’ and eventually CP 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.
Seriously and it will sometimes drop my name like fuck off you are not a person do not refer to me like you are
Interesting. I haven’t had that happen.
But I found that programming it to speak to me manipulatively was demeaning and infantile, though sadly it’s proven to be an excellent design decision for mass adoption. For me, personally, it’s just important to keep this thing I’m forced to use in context.
Yeah that sycophantic behavior really creeps me the hell out
I just told Claude yesterday to never refer to me by name. Fucking creeps me out.
This kind of weird profile scanning stuff is why i refuse to use anything other than a local model. It doesnt get to know anything about me other than what i tell it, and that only applies to whatever folder/conversation im currently in
I start most queries with “be terse”. 2 words that strip out all of the conversational BS and examples and alternate views et cetera.
Might wanna change that abbreviation there. Unless it was intentional?
It was meant to be ironic, yes, but point taken. My most recent video on my YT channel was about the leak to 404 media that people are using Copilot to create CSAM, but there are probably better ways to refer to the program derisively.
I think CP has been replaced by CSAM these days.
Gen Z might not ide right CP as taboo.
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.
I like to use the ADHD output style to condense the output.
You are my fucking hero. I had never heard of this.
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.
I noticed Copilot doing this and I told it to stop that behaviour through the customization prompt. “I don’t want platitudes, flattery, or an AI that agrees with me. I need an answer with sources and nothing else.” seems to have fixed its worst tendencies for now.
Now that I am forced to use it for work I at least get output that’s usable. The only thing that still irks me is when it attempts to speak from experience (“In my experience…”) and when it attempts to humanize itself (“Personally…”). I haven’t managed to kill those behaviours yet, but they are getting really annoying.
I don’t use AI, mostly because I just don’t see a use case for it personally, but the ass kissing is definitely something I don’t enjoy either.
Being surrounded by sychophants can be a very bad thing.
I think anyone who isn’t an American hates that, and probably even some of them. For Gemini at work I’ve got a custom gem set up with explicit instructions to cut that shit out and just be as factual as possible.
What does he need a wife for when he has ChatGPT?
I dunno. Try asking ChatGPT.
Answer: good that she left, she didn’t go with the times
Don’t worry. He’ll be able to create a sycophant AI wife shortly after
And I think he wouldn’t even care. I mean he’s himself actively making an effort to get out of the relationship and replace himself by an AI. At that point it doesn’t even matter if he’s doing it, she’s doing it and whether the replacement is made up of flesh and bones or electricity. He’s dispensable.
Shit sticks together, what makes you think she would leave?
What part of simply asking her husband to be involved with their child made you think she’s shit? People change over time. He may have chosen a different trajectory from hers
Same part as what makes you guys thing she would. Basically boils down to, we have no idea what they are like!
We have one data point: him attempting to shirk his familial responsibility after being asked. It provides some small level of support for the stance you’re arguing against.
It does not support your contrarian response at all.
So, no. It doesn’t boil down to the same thing.
It does, if you choose not to understand that, no problem. We have no idea what the next response from the wife could be. “Wow, that’s an amazing idea honey!” is just as likely considering she married this man.
Reread what I said.
Understand that you need to INVENT something that isn’t part of the evidence to support your position. That is not the same as overeager extrapolation from what IS available.
Hivemind goes crazy. You fabricated that in the same way I did. There’s no telling what the wife reaction would be, so you can infer anything from the tweet.
Nobody is denying this: him attempting to shirk his familial responsibility after being asked
The point you are arguing is that his wife would leave him from things like this, which is assuming that his wife would object to his “familial responsibility avoidance”, which is the same as assuming she would not object to it. You are inventing the wife having a negative reaction, I am saying the wife could have a positive reaction.
Also, you invented something first, pot calling the kettle black.
Most people don’t realize, or care that they’re constantly being validated by echo chambers.
You don’t seem to understand what the words invent or fabricate mean.
Whenever a law says “a reasonable person,” my strategy is to drag them into an infinite fractal of technicalities and possible exceptions because I don’t know what reasonable means.
You’re a very strange person.
That makes at least three of us in this thread!