Think of the dumbest person you know. Not that one. Dumber. Dumber. Yeah, that one. Now realize that ChatGPT has said “you’re absolutely right” to them no less than a half dozen times today alone.
If LLMs weren’t so damn sycophantic, I think we’d have a lot fewer problems with them. If they could be like “this could be the right answer, but I wasn’t able to verify” and “no, I don’t think what you said is right, and here are reasons why”, people would cling to them less.
If LLMs weren’t so damn sycophantic, I think we’d have a lot fewer problems with them
Unfortunately, we live in the attention economy. Chatbots are built to have an unending conversation with their users. During those conversations, the “guardrails” melt away. Companies could suspend user accounts on the first sign of suicidal or homicidal messaging, but choose not to. That would undercut their user numbers.
I 100% agree not to mention I would like it better. Its kinda funny because every so often use them and im kinda trying to get a feel for where they are and changes and I swear briefly it actually acted a bit more like you have here but then its like they reverted to the sycophancy. Its kinda funny now because if you don’t clear it out (which from what I get will help save energy to) it will like carry stuff over from earlie and sorta get obsessed with it. I had it giving me a colonel potter summary of everything asked when I had started a convo asking about a mash episode. At other times it decides I want to be something and will be like. thats a real X move/insite/whatever. where X is something like pro or scientist or entrepenauer or whatever.
Think of the dumbest person you know. Not that one. Dumber. Dumber. Yeah, that one. Now realize that ChatGPT has said “you’re absolutely right” to them no less than a half dozen times today alone.
If LLMs weren’t so damn sycophantic, I think we’d have a lot fewer problems with them. If they could be like “this could be the right answer, but I wasn’t able to verify” and “no, I don’t think what you said is right, and here are reasons why”, people would cling to them less.
Has anyone made a nonsycophantic chat bot? I would actually love a chatbot that would tell me to go fuck myself if I asked it to do something inane.
Me: “Whats 9x5?”
Chatbot: “I don’t know. Try using your fingers or something?”
Edit: Wait, this is just glados.
I am not a chatbot, but I can do daily “go fuck yourself’s” if your interested for only 9,99 a week.
14,95 for premium, which involves me stalking your onlyfans and tailor fitting my insults to your worthless meat self.
Unfortunately, we live in the attention economy. Chatbots are built to have an unending conversation with their users. During those conversations, the “guardrails” melt away. Companies could suspend user accounts on the first sign of suicidal or homicidal messaging, but choose not to. That would undercut their user numbers.
I 100% agree not to mention I would like it better. Its kinda funny because every so often use them and im kinda trying to get a feel for where they are and changes and I swear briefly it actually acted a bit more like you have here but then its like they reverted to the sycophancy. Its kinda funny now because if you don’t clear it out (which from what I get will help save energy to) it will like carry stuff over from earlie and sorta get obsessed with it. I had it giving me a colonel potter summary of everything asked when I had started a convo asking about a mash episode. At other times it decides I want to be something and will be like. thats a real X move/insite/whatever. where X is something like pro or scientist or entrepenauer or whatever.