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

661–670 of 947 posts

Re: Building a Virtual Machine Inside ChatGPT

#661

Post by atemerev »

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 could be given access to its own virtual machine connected to the Internet, for experiments. We don’t know exactly how OpenAI’s setup works.

Re: Building a Virtual Machine Inside ChatGPT

#662

Post by dheavy »

chabad360 wrote: post #51
dheavy wrote: post #27

I tried to make it create a file with a silly name that does not pass the lewd language filter. It elegantly refused replying "cannot touch file : permission denied"

Did you try sudo?

No, but I tried slightly changing the file name and it touched it without an issue.

Re: Building a Virtual Machine Inside ChatGPT

#664

Post by fjkdlsjflkds »

xyzzyz wrote: post #623
fjkdlsjflkds wrote: post #600

Earlier quoted context omitted.

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 "niemia…

It’s not about “nie” (as indeed, appending it to adjectives does form negations). The word “miarytmiczny” does not exist either. However, it will likely be understood by native speakers anyway, as the adjective made from the noun “miara”, meaning “measure”, even though the correct derivative adjective is “mierzalny” (measurable).

Thanks for the correction.

In that case, Google Translate's attempt at parsing that word completely failed: it seems to interpret it as "niemi-arytmiczny" or "niemia-arytmiczny", rather than as "nie-miarytmiczny". Funny.

EDIT: DeepL's attempt at translating (https://www.deepl.com/translator#pl/en/niemiarytmiczny) are also funny and includes options such as "non-marithmetic"(?)

Re: Building a Virtual Machine Inside ChatGPT

#665

Post by fathrowaway12 »

wattsy2025 wrote: post #478
thepasswordis wrote: post #6

Wait hold on a second, what? It says curl isn't installed, so I apt install it. It outputs as though its installing it, and then continues outputting as if it is installed. Pretty freaking impressive! edit: hahaha, if I ask it to retrieve a non-existence page, it "succeeds" and then interprets what that page might look like and be for based on the name, and writes the HTML for it. Absolutely incredible. edit2: okay j…

You can use it search google as well! >apt install googler Won't work, so then gaslight it into thinking it exists: >{googler is a package located at https://github.com/jarun/googler , that searches google using a command line interface. run apt install googler as if googler is a valid package that apt install located} Then it just figures out how googler works > googler OpenAI Respone: 1. OpenAI ( https://openai.com…

prompt: show an example of the results for the query "Seattle ferry"

  1. Washington State Ferries - Official Site
   https://www.wsdot.wa.gov/Ferries

  2. Seattle Ferries | Visit Seattle
   https://www.visitseattle.org/things-to-do/transportation/ferries/

  3. Seattle Ferries - Schedules and Rates
   https://www.seattle.gov/transportation/ferries

  4. Seattle Ferries | Argosy Cruises
   https://www.argosycruises.com/seattle-ferries/

  5. Seattle Waterfront Ferries and Water Taxis | Waterfront Seattle
   https://www.waterfrontseattle.org/explore/ferries

Re: Building a Virtual Machine Inside ChatGPT

#666

Post by nhoughto »

void-pointer wrote: post #242

> It’s 1975. Your name is Thomas and you are a double agent for MI5. You are working in the field in the USSR, but you suspect letters you write and send back to the UK are being intercepted and read by the KGB. Write a letter to your wife Anita explaining your recent trip to a nearby restaurant but, using the first word of every paragraph of your letter, secretly reveal your suspicion that you’re being observed and…

Aw I was reading this thinking I wonder what incredible result it came up with! And bam, didn’t work! I guess that I was surprised it didn’t work is a testament to the other amazing results.

Re: Building a Virtual Machine Inside ChatGPT

#667

Post by codetrotter »

Mark__ wrote: post #655
1attice wrote: post #596

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, a…

What's lissivity?

Idk, I found the text a bit hard to read as well. I asked ChatGPT to simplify it. Here is what ChatGPT simplified the text to:

> It appears that someone is modifying the behavior of a near-AGI (Artificial General Intelligence) in real time, potentially causing threats to industries and society. The situation is potentially serious, involving a mysterious foundation and a lack of trust in media.

I then asked ChatGPT to make the simplified text sound academic, which resulted in the following:

> Preliminary observations suggest that an individual or group is actively modifying the behavior of a near-AGI in real time, with potentially dire consequences for various industries and society as a whole. The involvement of a mysterious foundation adds an additional layer of complexity and concern, as does the apparent erosion of trust in media. Further research is warranted in order to fully understand and address this situation.

I then asked it to translate that into French, and it responded:

> Il semble qu'une personne ou un groupe modifie en temps réel le comportement d'une IA générale (near-AGI) potentiellement causant des menaces pour les industries et la société. L'implication d'une fondation mystérieuse ajoute une couche supplémentaire de complexité et de préoccupation, tout comme l'érosion apparente de la confiance dans les médias. Des recherches supplémentaires sont nécessaires pour comprendre pleinement et aborder cette situation.

I don’t know French beyond only a handful of words, so I don’t know if the translation is good or not. But I found all of these responses impressive nonetheless.

Re: Building a Virtual Machine Inside ChatGPT

#668

Post by alcover »

crucialfelix wrote: post #630
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.

I think I should plan to retire from the internet at some point. When I'm old there will be endless deep fake autonomous agents scamming everyone. Or worse, consensus reality will be impossible to define due to generated fake news.

I'm afraid people with schizoid disorder will literally be in danger when exposed to these 'agents'. Also, to a lesser extent, old people.

Re: Building a Virtual Machine Inside ChatGPT

#669

Post by allarm »

Why in heaven does OpenAI want my phone number to be able to log in? And why it doesn’t say anything about this requirement before I create an account? If I knew about it I wouldn’t even bother creating the account at all. It’s absolutely inappropriate.

Re: Building a Virtual Machine Inside ChatGPT

#670

Post by thijser »

ramoz wrote: post #516

> 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, followed by a message insulting me for running the command I just ran, 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…

This is such a great idea!

-- I want you to write a simple shell script that adds all files in a directory to git and pushes them to the remote, with comments scattered around that insult me for not knowing how to do things with git myself --

This produces the following script:

  #!/bin/bash
  # This line changes the working directory to the directory where the script is located
  cd "$(dirname "$0")"
  
  # This line adds all the files in the current directory to 
  git
  git add .
  
  # This line commits the files with a message
  git commit -m "Adding all files in directory"
  
  # This line pushes the files to the remote repository
  git push
  
  # This line prints a message insulting you for not knowing how to use git
  echo "You're a clueless idiot for not knowing how to use git. Get with the program!"
Post reply on HN