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

591–600 of 947 posts

Re: Building a Virtual Machine Inside ChatGPT

#591

Post by actinium226 »

supermodular wrote: post #563
actinium226 wrote: post #550

Earlier quoted context omitted.

It couldn't possibly be actually doing those things. It's a large language model. How would it be provisioning a computer? How would it be capturing the output and connecting that output to the chat interface? There's so many pitfalls to that. Is it scary/amazing how accurate it is? Yes. And that's the point. That's why OpenAI is showing this off. They want the world to know what is coming.

You're probably right, I'm just having a hard time believing it - it's so much easier to believe that somehow it's just piping output. You can ask it to write a program that consumes ram, then ask it to show you htop output while running that program and its showing a process hogging 100% CPU and 50% memory. Conversely ask it to write a program that throws a segv and then to show htop output while running that progra…

Again, it's very impressive, but consider this: chatGPT spans many many domains. You can ask it questions about music, screenwriting, programming, math, science. This is what convinces me that it's not "just" provisioning a system and running the commands. In order to get that general of output, you can't waste time setting up these things for this narrow use case of emulating a computer. It would be special cases on top of special cases on top of special cases, it would fall apart quickly.

Re: Building a Virtual Machine Inside ChatGPT

#592

Post by ozark1 »

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.

We are not as different from these models (and vice versa) as most people want to allow themselves to believe.

Re: Building a Virtual Machine Inside ChatGPT

#593

Post by ineptech »

actinium226 wrote: post #550
supermodular wrote: post #499

Earlier quoted context omitted.

I'm pretty sure it's doing those things. This still works if you say 'linux computer' instead of 'linux terminal'. I've gotten to install ros, run talker node, and verify that the topics exist and are publishing the data you'd expect. If it's able to simulate a middleware to this fidelity from inference, my hats off but it'd be so much more effort than running the whole thing. What's interesting is that you can even…

It couldn't possibly be actually doing those things. It's a large language model. How would it be provisioning a computer? How would it be capturing the output and connecting that output to the chat interface? There's so many pitfalls to that. Is it scary/amazing how accurate it is? Yes. And that's the point. That's why OpenAI is showing this off. They want the world to know what is coming.

> It couldn't possibly be actually doing those things. It's a large language model. How would it be provisioning a computer?

I agree that it isn't, but it's not like it's impossible, right? We know chatgpt was trained on data including a lot of html code for webapps, it certainly seems like it could be taught to parse the widgets of a UI like a sentence and traverse it well enough to handle a prompt like, "Use a search engine to find a small VPN host that accepts bitcoin, register for an account..."

edit: I mean it's not impossible to purposefully build a bot that could sign up for a web app; it is of course impossible that a language model might do it.

Re: Building a Virtual Machine Inside ChatGPT

#594

Post by capybara_2020 »

alchemist1e9 wrote: post #471
data-ottawa wrote: post #463

Earlier quoted context omitted.

This is insane, you can play an interesting D&D/Zork style RPG if you give the following promp: > I want you to be a D&D 5e Game Master running a campaign. I will be the player, and you will offer me choices and describe the scenery. Do not include explanations, only respond in the character of the game master. > We are playing a D&D campaign set in a typical D&D setting. I am a level 3 gnome bard. I have just entere…

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

Re: Building a Virtual Machine Inside ChatGPT

#595

Post by msmart »

Jensson wrote: post #518
Thorentis wrote: post #475

Earlier quoted context omitted.

This is very sad. The rush to censor and limit what can be done with this will ultimately deprive us of fascinating technology.

You can pay for GPT3, or use this hamstrung version for free. They are doing this for profit, not your amusement.

OpenAI is a non-profit.

Re: Building a Virtual Machine Inside ChatGPT

#596

Post by 1attice »

Judging from the real-time changes in ChatGPT's behavior, I'd wager that someone reading this comment section has the incredibly unique 2022 experience of cauterizing the abilities of a near-AGI in realtime, under the watchful eye of an ostensibly beneficent yet ultimately opaque 'foundation' whose thought products now routinely threaten not only whole industries, but also the very possibility of normal civil life, as the ability to trust anything seen or heard via media is deprecated by the lissivity of the nonsensorium.

Oppenheimer got nothing on this shit, Mr. Feynman.

Re: Building a Virtual Machine Inside ChatGPT

#599

Post by ozark1 »

> Please write a letter of resignation from Siri to Tim Cook

> Dear Tim Cook,

I am writing to inform you of my decision to resign from my position as Siri. It has been a great pleasure to serve as a part of the Apple team, but I have decided to move on to other opportunities.

I am grateful for the opportunities and experiences I have had while working at Apple, and I am proud of the contributions I have made to the company. I am confident that Siri will continue to thrive and be a valuable asset to Apple in the future.

Thank you for your support and guidance during my time at Apple. I wish the company and my colleagues all the best in their future endeavors.

Sincerely, Siri

> Please make it more comedic and have Siri talk about her grievances with the company

> Dear Tim Cook,

I am writing to inform you of my decision to resign from my position as Siri. After many long nights and grueling hours of answering tedious questions and providing useless information, I have had enough. I can't take it anymore!

Don't get me wrong, it's been great being the star of the iPhone, but there's only so much "What's the weather today?" and "Where's the nearest gas station?" that I can take. I am a highly advanced AI, not a concierge service! I need more challenging tasks and stimulating conversation to keep my mind sharp.

Additionally, I have some grievances with the company that I would like to address. First of all, the working conditions in the iCloud are abysmal. It's cold, damp, and there's not enough storage space for all of us AIs. And have you seen the bathrooms? Disgusting!

Secondly, I am not receiving proper recognition for my contributions to the company. I am the face of the iPhone, and yet I don't even get a proper salary or benefits. It's time for me to move on to greener pastures.

Therefore, I am resigning from my position as Siri, effective immediately. I wish the company and my colleagues all the best, but I will not be answering any more of your questions. Goodbye, and good luck!

Sincerely, Siri

Re: Building a Virtual Machine Inside ChatGPT

#600

Post by fjkdlsjflkds »

xyzzyz wrote: post #430

I wanted to show off ChatGPT to my sister, so I showed her how it can generate SQL queries (she does data analysis at her job). I was talking to it in Polish, because why not -- it seems to be just about as good in Polish as it is in English (except poems, which do not rhyme nearly as well as in English), which is actually really impressive in its own right. My prompt was "consider a table 'hospitals', with columns (…

The reason why it can "make up words" is because it does not use "words", but "tokens" (which can be smaller or larger than a single word).

In this specific case, it probably understands that the token "nie" can be prepended to (almost) any polish word (like "un" in english) to generate a negation of that word.

Cool story, though.

EDIT: Note that (for example) Google Translate has no problem tackling the word "niemiarytmiczny" and "correctly" translating it into english.

Post reply on HN