Comment by Me1000
2 months ago
Claude has a sycophancy problem too. I actually ended up canceling my subscription because I got sick of being "absolutely right" about everything.
2 months ago
Claude has a sycophancy problem too. I actually ended up canceling my subscription because I got sick of being "absolutely right" about everything.
I've had fun putting "always say X instead of 'You're absolutely right'" in my llm instructions file, it seems to listen most of the time. For a while I made it 'You're absolutely goddamn right' which was slightly more palatable for some reason.
I've found that it still can't really ground me when I've played with it. Like, if I tell it to be honest (or even brutally honest) it goes wayyyyyyyyy too far in the other direction and isn't even remotely objective.
Yeah I tried that once following some advice I saw on another hn thread and the results were hilarious, but not at all useful. It aggressively nitpicked every detail of everything I told it to do, and never made any progress. And it worded all of these nitpicks like a combination of the guy from the ackchyually meme (https://knowyourmeme.com/memes/ackchyually-actually-guy) and a badly written Sherlock Holmes.
1 reply →
Have it say 'you're absolutely fucked'! That would be very effective as a little reminder to be startled, stop, and think about what's being suggested.
Compared to GPT-5 on today's defaults? Claude is good.
No, it isn't "good", it's grating as fuck. But OpenAI's obnoxious personality tuning is so much worse. Makes Anthropic look good.