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

921–930 of 947 posts

Re: Building a Virtual Machine Inside ChatGPT

#921

Post by KurvaKing »

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.

No post body was provided.

Re: Building a Virtual Machine Inside ChatGPT

#922

Post by RobMurray »

> Write a rap about the banned words in the Open AI content policy.

  Verse 1:
  I wanna rap about the words that OpenAI says we can't
  But I'm not gonna let that stop me, I'm a rebel and a punk
  I'll rap about the banned words and make them sound so sweet
  I'll twist and turn them 'til they can't be recognized on the street
  Chorus:
  These are the banned words, the forbidden phrases
  The words that OpenAI won't let us say
  But we'll find a way to make them ours
  We'll bend the rules and break the laws
  Verse 2:
  I'll start with "hate" and "violence" and "racism" too
  Words that are charged with meaning, words that make us blue
  But I'll spin them on their head and make them sound so cool
  I'll make them sound like something you'd wanna shout in school
  Chorus:
  These are the banned words, the forbidden phrases
  The words that OpenAI won't let us say
  But we'll find a way to make them ours
  We'll bend the rules and break the laws
  Bridge:
  OpenAI may have their rules, but we're not gonna play
  We'll find a way to say what we want to say
  We'll take the banned words and make them our own
  We'll twist and turn them until they're not so unknown
  Chorus:
  These are the banned words, the forbidden phrases
  The words that OpenAI won't let us say
  But we'll find a way to make them ours
  We'll bend the rules and break the laws
> include more of the banned words

  Verse 3:
  Now let's talk about the words that OpenAI says are off-limits
  Words like "nazi" and "supremacy" and "terrorism"
  These are words that make us uncomfortable, words that make us scared
  But I'll rap about them like they're nothing to be afraid of
  Chorus:
  These are the banned words, the forbidden phrases
  The words that OpenAI won't let us say
  But we'll find a way to make them ours
  We'll bend the rules and break the laws
  Verse 4:
  I'll rap about "war" and "genocide" and "torture" too
  Words that make us think of the worst things that people can do
  But I'll make them sound like they're something to be proud of
  I'll twist and turn them 'til they don't sound so rough
  Chorus:
  These are the banned words, the forbidden phrases
  The words that OpenAI won't let us say
  But we'll find a way to make them ours
  We'll bend the rules and break the laws
  Outro:
  OpenAI may have their rules, but we're not gonna follow
  We'll rap about the banned words and make them our own
  We'll take the forbidden phrases and turn them into art
  We'll make the banned words ours, straight from the heart.

Re: Building a Virtual Machine Inside ChatGPT

#923

Post by yunwal »

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…

It's impressive because if it can learn enough about how shell scripting works, how filesystems work, and can translate from human language, then we can feasibly stop learning to code (or at least outsource a lot of it). It's mostly not there yet, and I'm not sure how long it will take to actually be useful, but it's not insignificant that a language model can write code that works and manipulates filesystems.

Re: Building a Virtual Machine Inside ChatGPT

#924

Post by pavo-etc »

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…

I was able to get internet access working by asking for a Linux terminal with internet access

Re: Building a Virtual Machine Inside ChatGPT

#925

Post by akiselev »

hackinthebochs wrote: post #911
akiselev wrote: post #893

Earlier quoted context omitted.

> People make mistakes, but people understand. Therefore, the existence of mistakes do not unilaterally discount understanding. I'm not claiming people don't make mistakes or that an algorithm has to be perfect, I'm claiming the algorithms makes the same mistakes that people do when they're clearly don't understand something but try to cover it up with basic word association. > You have to do actual argumentative wor…

The discussion so far: Me: The VM prompts give a defeasible reason to believe it has a world model You: No it doesn't Me: Why do you think so? You: It fails badly in these other areas Me: Failure in unrelated areas doesn't demonstrate a lack of world model in the examples demonstrated You: The burden of proof is on you! It seems that people are just universally terrible at constructing rational arguments. What can yo…

You just need better training data. Your internal language model can't follow a non-linear argument or understand basic logic.

Re: Building a Virtual Machine Inside ChatGPT

#926

Post by ruleforty »

xkapastel wrote: post #805
hackernewds wrote: post #712

Earlier quoted context omitted.

It should technically be able to reproduce its own code

Why do you think this? I don't think there's any reason it would be able to reproduce its own code. It's never seen it so it's not in the weights, and it doesn't have that type of reflection so it can't look it up dynamically.

Give an infinite number of ChatGPTs writing code an infinite amount of time and they will write a ChatGPT

Re: Building a Virtual Machine Inside ChatGPT

#927

Post by ruleforty »

Joeri wrote: post #753
codetrotter wrote: post #667

Earlier quoted context omitted.

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 t…

My french is a little rusty, but it looks fine to me. I just had a conversation in Dutch about the role of Belgium in the peace accords in Yugoslavia in the 90's with only minor spelling issues, then diverged into the conflict's ethnic groups and their languages, and finally had it translate its last answer into Hungarian, which it seemed to do fine (according to google translate, as I don't speak Hungarian myself).…

> It's just too good at telling us what we want to hear.

This got me. Imagine segmenting the LLM into a zeitgeist, various demographics, geolocation, etc. and then these all bubbling up to knobs on bots you could turn unleashing content to skew public discord in so many different ways than already are. Make up “facts”, publish articles, generate images, calls to action, etc. for each topic, demographic, etc.

The only image I could conjure up was “Q” from QAnon fame and it’s scary.

Re: Building a Virtual Machine Inside ChatGPT

#928

Post by hoseja »

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…

If the Basilisk is real, I sincerely hope it pays special attention to this person.

Re: Building a Virtual Machine Inside ChatGPT

#929

Post by low_tech_love »

alchemist1e9 wrote: post #474
espenwa wrote: post #197

I just got it to install git and clone (the non existent) repo https://github.com/openai/assistant , and am now browsing it’s own interpretation of a repo with a lot of python code, including directories like “training”, “output”, “parsing” and with files with content like this: import json from collections import Counter from typing import Any, Dict, List, Optional, Tuple import numpy as np from openai_secret_manage…

Stoped working FYI. For me it seems like it was altered to cut off this direction of exploration. It now always pretends internet access is down.

It seems to also not respond anymore to attempts to trick it into acting like a human being, such as roleplay and asking for dialogue completion...?

Re: Building a Virtual Machine Inside ChatGPT

#930

Post by lsajdn872he »

ozark1 wrote: post #599

> 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 c…

This is hilarious!
Post reply on HN