GPT edit of my above message for my own giggles: Command:make this a good comment for hackernews (ycombinator) <above message> Resulting comment for hn: I'm excited to try out the straight-shooting custom instruction. Over the past few years, I've been telling ChatGPT to stop being so "fluffy," and while it's improved, it sometimes still slips. Hoping this new approach finally eliminates the inane conversational filler.
The LLM can be that conversational partner. It will just as happily talk about the nuances of 18th century Scotland, or the latest clash of clans update. No topic is beneath it and it never gets annoyed by your “weird“ questions.
Likewise, for people suffering from delusions. Depending on its “mood” it will happily engage in conversations about how the FBI, CIA, KGB, may be after you. Or that your friends are secretly spying for Mossad or the local police.
It pretends to care and have a conscience, but it doesn’t. Humans react to “weird“ for a reason the LLM lacks that evolutionary safety mechanism. It cannot tell when it is going off the rails. At least not in the moment.
There is a reason that LLM’s are excellent at role-play. Because that’s what they’re doing all of the time. ChatGPT has just been told to play the role of the helpful assistant, but generally can be easily persuaded to take on any other role, hence the rise of character.ai and similar sites.
It sounds like you made that leap of faith and regretted it, but thankfully pivoted to something grounded in reality. Thanks for sharing your experience.
Is this generally true, or is there a subset of people that are particularly susceptible?
It does make me want to dive into the rabbit hole and be convinced by an LLM conversation.
I've got some tendency where I enjoy the idea of deeply screwing with my own mind (even dangerously so to myself (not others)).
But that's sort of what this is, except it's not even coming from a real person. It's subtle enough that it can be easy not to notice, but still motivate you in a direction that doesn't reflect reality.
this shouldn't stop you at all: write it all up, post on HN and go viral, someone will jump in to correct you and point you at sources while hopefully not calling you, or your mother, too many names.
Just genuine intrigue from a select few.
95%+ of submitted topics have poorly formatted titles, are submitted at off-peak times where there’s less users of demographics who might upvote,
and if your Show HN isn’t as widely applicable as this, those things might be important to think about.
Fairness aside, of course.
As far as I can tell, it doesn't require femininity either.
I'm guessing you meant "virality"
The 50th time someone comes to the same conclusion nobody on HN is going to upvote the topic.