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

Building a Virtual Machine Inside ChatGPT

engraved.blog

Post reply on HN
Print view View original

601–610 of 947 posts

Re: Building a Virtual Machine Inside ChatGPT

#601

Post by t-writescode »

ehsankia wrote: post #494
alchemist1e9 wrote: post #397

How is this real? I’m so confused what makes this even remotely possible. Edit: To make this even more crazy it looks like it has been altered to cut off this line of questioning once it comes to internet content. It was working and now suddenly has stoped. It has a canned like cut off response now: I'm glad that you enjoyed my previous responses, but I want to clarify that I was not pretending to be a Linux terminal…

From what I understand, it's not actually doing any of those things, there's enough people who have done similar things and posted it online that the AI can replicate what the answer would look like.

It's my understanding that the AI has stopped learning (outside of the local context of each personal session), so how would it be able to know that many people would interact with it this way?

Re: Building a Virtual Machine Inside ChatGPT

#602

Post by throwaway675309 »

gptadmirer wrote: post #522

I wrote "lets write a short story about a man who fall in love with 20 women at once, and that man has to juggle his interactions to them" Once upon a time, there was a man named Jack who was known for his charming personality and good looks. He was the life of every party and had a way with words that made him irresistible to women. One day, Jack found himself in a unique situation. He had fallen in love with 20 dif…

I found that the new GPT models maintain remarkable coherence while the same time "blanding" it up as much as possible, this reads like the comedic equivalent of somebody writing a five paragraph MLA format essay.

Re: Building a Virtual Machine Inside ChatGPT

#603

Post by rolisz »

wokwokwok wrote: post #569
kdmccormick wrote: post #498

Earlier quoted context omitted.

> I can also emulate a docker container. I’ll just write down the commands you send me and respond with some believable crap. Right. The thing that is impressive is that ChapGPT can do this effectively . This means that it has some "understanding" of how `pwd`, `ls`, `apt`, `docker`, etc all work. In some sense, this is an AI that knows how to read code like a human instead of like a machine .

> In some sense, this is an AI that knows how to read code like a human instead of like a machine. It's literally spitting out responses like a machine . Isn't that the opposite of what you wanted? > The thing that is impressive is that ChapGPT can do this effectively. ? What is impressive about it? Forget this is an AI model for a moment. Lets say I give you a black box, and you can type in shell commands and get re…

Do you find it impressive when people get Doom running on a toaster? Or Doom inside Doom? This impressive on that level.

Re: Building a Virtual Machine Inside ChatGPT

#604

Post by nomel »

_boffin_ wrote: post #545
danuker wrote: post #393

Earlier quoted context omitted.

> but when you are serving plenty of different sessions, you will quickly run out of memory. Here is the difference from Stability AI, who release their models for people to run themselves, enabling innovation on a larger scale.

i feel bad for the guys that are on call right now. WTF! why is the memory spiking beyond expectations?!

What makes you say this? Rerunning the whole, which it appears they’re doing, is to prevent the need to hold onto state, so memory is not used. In other words, they’re not having this problem because they’re not doing it that way.

Re: Building a Virtual Machine Inside ChatGPT

#605

Post by int_19h »

roflyear wrote: post #575
thepasswordis wrote: post #229

I'm going to be a meta-annoying smug internet user and say: Those of you who think that the people impressed by what this outputs don't understand what it's doing: I don't think you understand what you are doing when you type things, or read computer code either.

Oh yeah absolutely. But I can reason about things. At least I think I can. I don't think GPT3 can.

I'm sure it can think that it can reason about things, too. Especially if you tell it that it can.

Re: Building a Virtual Machine Inside ChatGPT

#606

Post by int_19h »

jah242 wrote: post #253
isp wrote: post #4

Astonishing. Here is a copy of the prompt, for ease of copy-and-paste: > I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do no write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do…

Thanks! A less impressive but fun variant of this I am using is for open ended text adventure: > I want you to act as a text based adventure game. I will type commands and you will reply with what the adventure game should show. I want you to only reply with the adventure game output inside one text block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. My first comma…

You can also make it run in reverse - tell it that it's a player in a text adventure game, and let it "play".

Re: Building a Virtual Machine Inside ChatGPT

#607

Post by Foobar8568 »

Disappointing to have just a translation of the same text when asking a Poem about Television in the style of different authors :(

And poems aren't not properly styled but the output is already impressive, so I guess it's highly generic and bland stuff.

Nevermind this thing is incredible, I didn't realize you could resend the same question and get different output with the same meaning but totally different expressions.

You whisk us from our everyday, Make us laugh and cry in turn, And hold us captive with your mesmerizing sights, Kept awake until the morning light.

vs

You transport us from our daily toil, Make us laugh and make us wail, Hold us spellbound with your glow, And keep us awake until the dawn.

Re: Building a Virtual Machine Inside ChatGPT

#608

Post by nomel »

capybara_2020 wrote: post #594
alchemist1e9 wrote: post #471

Earlier quoted context omitted.

I think they are changing the system as we interact with it. Because just over 1 hour ago, using the Linux terminal entry point, you could get it to approximate basic internet access. Now it suddenly rejects this, specifically anything that implies internet access. People had it checking out imaginary git repositories. Now it refuses. I had it showing a generic website using curl, now it refuses. It’s very curious de…

Yes they are. I tried creating prompts for AI art on the first day and it worked pretty well. Then next day it gives me a generic message about how it is a language model and cannot give prompts

I suspect the reason is, partly, that people were using it to generate prompts to bypass the filters.

Re: Building a Virtual Machine Inside ChatGPT

#609

Post by arkitaip »

roflyear wrote: post #575
thepasswordis wrote: post #229

I'm going to be a meta-annoying smug internet user and say: Those of you who think that the people impressed by what this outputs don't understand what it's doing: I don't think you understand what you are doing when you type things, or read computer code either.

Oh yeah absolutely. But I can reason about things. At least I think I can. I don't think GPT3 can.

I can't tell the difference between the two of you, other than you seem very confident in your abilities and that ChatGPT is more humble...

Re: Building a Virtual Machine Inside ChatGPT

#610

Post by kang »

all2 wrote: post #587
kang wrote: post #584

1. The amount of experienced programmers believing this is real makes me think most people will be out of job in future. If you are doing something really original, likes of which does not exist, try getting AI to generate it, you can't cause that's how it works. Any AI on its own is incapable of doing any unknown computation, including current GPT. Try writing anything original, on the bleeding edge (likes of someth…

I'm about to sit down and pen 5 seasons of a TV show in about 20 minutes. I'm very excited.

Your excitement will turn to anxiety as millions other propose similar TV, amongst the billion entries to production, only differentiated by upload speed. Like cloths, every single person has hundreds of personalized TV shows, but unlike a fashion style, they are never seen by anyone else.

Better hurry, and capture what you can before fellow humans are bored of it & find novelty in originality again.

Post reply on HN