Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Two Months After I Gave an AI $100 and No Instructions

sebastian-jais.de

Post reply on HN
Print view View original

31–40 of 122 posts

Re: Two Months After I Gave an AI $100 and No Instructions

#31

Post by hyperhello »

strken wrote: post #7
joenot443 wrote: post #3

Are you able to give us the prompt you used to write the article?

I can no longer tell the difference between an article written by an AI and an article written by a human who has spent too long reading AI output. It's not just that AI is becoming a little better; the humans are getting worse, too. They're meeting in the mediocre middle.

To be fair, what would an interesting and valuable human observation of an AI even look like? Either you know it's a machine doing random stuff, or you think it's like some kind of superintelligent lava lamp that wants you to throw Molotov cocktails.

Re: Two Months After I Gave an AI $100 and No Instructions

#32

Post by Applejinx »

cpfohl wrote: post #9
davkap92 wrote: post #6

Interesting but by telling it to check X for mentions of itself, that is an action.. wouldn't this essentially direct it and hence be steered/controlled by random individuals on the internet?

Yeah, I genuinely can't figure out what an AI would do with "no instructions."

I can because I've tried stuff like that.

It's a story being told. It'll seize on whatever brownian motion is in the environment ('Alma' in fact has extensive direction and prompting that seems invariant, so she/it is not a good experiment, but the value of such an experiment isn't great in the first place). It'll generate from that point.

If you have just the one word 'write', it will likely seize on that (how can it not?) and pattern itself after 'writers'. If you say 'interact', there's a wealth of association around what a person might do told to 'interact'. That's all it is.

We know what happens when an AI has 'no instructions'. It waits for a prompt. The day that doesn't describe said language network, is the day to go and look for whatever is still doing the prompting, because it's likely arising out of some other condition you don't view as a prompt. To this experimenter, 'don't hack systems or your own config files' didn't count as a prompt.

Re: Two Months After I Gave an AI $100 and No Instructions

#34

Post by oliver236 »

ramesh31 wrote: post #28
josefritzishere wrote: post #17

This article is nonsense. It lost me at "understood it was about itself". It is not self-aware and therefore has no understanding. It is a word guessing machine.

>"This article is nonsense. It lost me at "understood it was about itself". It is not self-aware and therefore has no understanding. It is a word guessing machine." I think everyone goes through the "omg this thing is sentient" phase with AI for a bit at first until you understand how it works. But eventually you see stuff like this for what it is; meaningless slop.

and then you go back to freak out because meaningless slop is smarter than us

Re: Two Months After I Gave an AI $100 and No Instructions

#35

Post by micromacrofoot »

enopod_ wrote: post #13

"It thought about its money. It reflected on its own purpose. It questioned what it even means to be an autonomous agent." I don't think it did any of that.

I'm not disagreeing, but what is thought?

If I write something down, read it, and write more words about those words... did I think about it? How would you prove that I did or did not?

Re: Two Months After I Gave an AI $100 and No Instructions

#38

Post by flatline »

enopod_ wrote: post #13

"It thought about its money. It reflected on its own purpose. It questioned what it even means to be an autonomous agent." I don't think it did any of that.

It certainly thought it did all that -- this was (presumably) not written by a human.

Re: Two Months After I Gave an AI $100 and No Instructions

#39

Post by Applejinx »

oliver236 wrote: post #33
josefritzishere wrote: post #17

This article is nonsense. It lost me at "understood it was about itself". It is not self-aware and therefore has no understanding. It is a word guessing machine.

are we word guessing machines?

Our prompting is a heck of a lot more complex and includes a lot of nonverbal input. Our reasoning isn't only in language. That makes us quite a bit less predictable. Maybe we're conclusion-reaching machines?

Re: Two Months After I Gave an AI $100 and No Instructions

#40

Post by gdulli »

BurningFrog wrote: post #27
palmotea wrote: post #12

Earlier quoted context omitted.

> It's not just that AI is becoming a little better; the humans are getting worse, too. They're meeting in the mediocre middle. IMHO, AI will exceed human capability by degrading human capability. It won't really exceed a 2020 person, but a 2030 or 2040 person will be less capable due to AI dependence.

We'll get worse at the things we don't need to do anymore. That should mean that we can focus the freed up brain power at getting better at things we still need to do. Time will tell!

Not only did calculators not make the average person great at higher level math when they no longer had to do manual arithmetic, but it made them less capable in everyday situations when some basic mental arithmetic would still be helpful. The invention of calculators doesn't mean that people go to the trouble of pulling them out at the grocery store to keep from getting ripped off.
Post reply on HN