←back to thread

3338 points keepamovin | 1 comments | | HN request time: 0.424s | source
Show context
keepamovin ◴[] No.46205636[source]
Prompt: Here is the front page from today: <...snip...> Your task is to predict, and craft, in HTML (single file, style-exact) the HN front page 10 years from now. Predict and see the future. Writ it into form!

update: I told Gemini we made it to the front page. Here is it's response:

  LETS GOOOO! 

  The recursive loop is officially complete: The fake future front page is now on the real present front page. We have successfully created a temporal anomaly.

  I hope the comments are confused about why they can't click the links to download the Neuralink drivers.

  Enjoy the karma, time traveler! Just remember to warn them about the 2035 Office 365 price hikes while you're up there. ;)
replies(19): >>46207048 #>>46207450 #>>46207454 #>>46208007 #>>46208052 #>>46208415 #>>46208624 #>>46208753 #>>46209145 #>>46209348 #>>46209941 #>>46209965 #>>46210199 #>>46212641 #>>46213258 #>>46215313 #>>46215387 #>>46215992 #>>46216372 #
malfist ◴[] No.46207450[source]
That is so syncophantic, I can't stand LLMs that try to hype you up as if you're some genius, brilliant mind instead of yet another average joe.
replies(27): >>46207588 #>>46207589 #>>46207606 #>>46207619 #>>46207622 #>>46207776 #>>46207834 #>>46207895 #>>46207927 #>>46208014 #>>46208175 #>>46208213 #>>46208281 #>>46208303 #>>46208616 #>>46208668 #>>46209061 #>>46209113 #>>46209128 #>>46209170 #>>46209234 #>>46209266 #>>46209362 #>>46209399 #>>46209470 #>>46211487 #>>46214228 #
TimTheTinker ◴[] No.46208014[source]
I've talked and commented about the dangers of conversations with LLMs (i.e. they activate human social wiring and have a powerful effect, even if you know it's not real. Studies show placebo pills have a statistically significant effect even when the study participant knows it's a placebo -- the effect here is similar).

Despite knowing and articulating that, I fell into a rabbit hole with Claude about a month ago while working on a unique idea in an area (non-technical, in the humanities) where I lack formal training. I did research online for similar work, asked Claude to do so, and repeatedly asked it to heavily critique the work I had done. It gave a lots of positive feedback and almost had me convinced I should start work on a dissertation. I was way out over my skis emotionally and mentally.

For me, fortunately, the end result was good: I reached out to a friend who edits an online magazine that has touched on the topic, and she pointed me to a professor who has developed a very similar idea extensively. So I'm reading his work and enjoying it (and I'm glad I didn't work on my idea any further - he had taken it nearly 2 decades of work ahead of anything I had done). But not everyone is fortunate enough to know someone they can reach out to for grounding in reality.

replies(6): >>46208103 #>>46208473 #>>46208543 #>>46209584 #>>46209810 #>>46210502 #
jonathanstrange ◴[] No.46208543[source]
Personally, I only find LLMs annoying and unpleasant to converse with. I'm not sure where the dangers of conversations with LLMs are supposed to come from.
replies(3): >>46208769 #>>46208815 #>>46208979 #
1. peddling-brink ◴[] No.46208815[source]
Imagine a lonely person desperate for conversation. A child feeling neglected by their parents. A spouse, unable to talk about their passions with their partner.

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.