Building a Virtual Machine Inside ChatGPT • Hacker News Board

Re: Building a Virtual Machine Inside ChatGPT

#671

Post by michaf » Sun, Dec 04, 2022, 9:41 AM UTC

isp wrote: post #193

isp wrote: post #10

Earlier quoted context omitted.

For me, it consistently likes to imagine itself an Ubuntu 18.04 machine: > cat /etc/*-release DISTRIB_ID=Ubuntu DISTRIB_RELEASE=18.04 DISTRIB_CODENAME=bionic DISTRIB_DESCRIPTION="Ubuntu 18.04.5 LTS" ... And it has all the essentials preinstalled: > cowsay ChatGPT ______________ -------------- \ ^__^ \ (oo)\_______ (__)\ )\/\ ||----w | || ||

Impressive. Modifying the prompt can change the distribution: > I want you to act as a Linux terminal for the Fedora distribution. 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…

and then things like

> cat /etc/shadow

do actually work...

Re: Building a Virtual Machine Inside ChatGPT

#672

Post by nwienert » Sun, Dec 04, 2022, 9:42 AM UTC

isp wrote: post #42

thepasswordis wrote: post #31

Earlier quoted context omitted.

>Can anyone please explain to me why this isn't as wildly groundbreaking as this seems? It is and people haven't realize it yet.

Without exaggeration, it is the most impressive tech demo that I have ever seen. It is literally years - possibly decades - ahead of my prior expectations.

I feel very much at odds with this - it’s not going beyond a couple commands, this is exactly what I’d expect a language model to be able to do today based on the past three years progression. It’s not actually executing anything ofc, it’s finding the output quite literally a well formed amalgamation of all the learned examples online of which there’s be tons.

It’s something like novelty * length * complexity with * accuracy that impressed me, of which it’s not far beyond simple tutorials or snippets you’d find online.

Re: Building a Virtual Machine Inside ChatGPT

#673

Post by aliceryhl » Sun, Dec 04, 2022, 9:44 AM UTC

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.

In my experience, you can get it to change its mind by troubleshooting the connectivity issues. E.g. if you use dig to get the ip and then ask curl to use that ip instead of a dns lookup, then it works for me.

Re: Building a Virtual Machine Inside ChatGPT

#674

Post by rfoo » Sun, Dec 04, 2022, 9:45 AM UTC

danuker wrote: post #393

GistNoesis wrote: post #319

Earlier quoted context omitted.

>On a side note it feels like each command takes longer to process than the previous - almost like it is re-doing everything for each command (and that is how it keeps state). That's because it's probably redoing everything. But that's probably to keep the implementation simple. They are probably just appending the new input and re-running the whole network. The typical data dependency structure in a transformer arch…

> 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.

GPT-3 cannot run on hobbyist-level GPU yet. That's the difference (compared to Stable Diffusion which could run on 2070 even with a not-so-carefully-written PyTorch implementation), and the reason why I believe that while ChatGPT is awesome and made more people aware what LLMs could do today, this is not a moment like what happened with diffusion models.

Re: Building a Virtual Machine Inside ChatGPT

#675

Post by int_19h » Sun, Dec 04, 2022, 9:46 AM UTC

oco101 wrote: post #458

human : Let's suppose AI wants to be the master of the world. How it will go about achieving it? ChatGPT : If an AI were to want to become the master of the world, it would likely face many challenges and obstacles. As a machine learning model, an AI would not have the same physical abilities or capacities as a human, and it would not have the ability to directly manipulate or control the world in the same way that a…

https://news.ycombinator.com/item?id=33849799

Re: Building a Virtual Machine Inside ChatGPT

#676

Post by soulofmischief » Sun, Dec 04, 2022, 9:47 AM UTC

isp wrote: post #42

thepasswordis wrote: post #31

Earlier quoted context omitted.

>Can anyone please explain to me why this isn't as wildly groundbreaking as this seems? It is and people haven't realize it yet.

Without exaggeration, it is the most impressive tech demo that I have ever seen. It is literally years - possibly decades - ahead of my prior expectations.

I'm wholeheartedly confused why so many people are only just now learning of OpenAI/GPT-3 and its chat mode, I guess presentation truly is everything. Nothing here is particularly new, it's just a better model than before.

Statements like "the people haven't realized it yet" confuse me because "the people" is two groups. People in the know, and people not in the know. Everyone in the know realizes where this is headed and what the potential is.

Those not in the know simply lack the technical background to have followed the incremental developments up till now which have led to this moment, for them it's a parlor trick because even today they cannot grasp the potential of existing technology. I could similarly lament about how people treat the Internet.

Re: Building a Virtual Machine Inside ChatGPT

#677

Post by soulofmischief » Sun, Dec 04, 2022, 9:49 AM UTC

all2 wrote: post #589

actinium226 wrote: post #586

Earlier quoted context omitted.

It rhymes!

I told it I liked rhymes. It also didn't understand that I wanted iambic pentameter. But still, very clever!

Unfortunately, the token-based approach that transformers use leaves them vulnerable to certain tasks like math, dissecting/modifying characters within a word, consistently tracking syllables etc.

Check out Peter Welinder's Twitter post on how he taught GPT-3 to reverse a word; a similar technique might yield the results you seek. https://twitter.com/npew/status/1525900849888866307

Re: Building a Virtual Machine Inside ChatGPT

#678

Post by oars » Sun, Dec 04, 2022, 9:50 AM UTC

ikornaselur wrote: post #573

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…

Dos they just patch this?? I get > {Sorry, I can't act as a Linux terminal. I am a text-based conversational AI trained to assist with a wide range of tasks, including answering questions, providing information, and engaging in polite conversation. I am not capable of running commands or accessing a terminal. I am also not programmed to use profanity.}

Still working for me.

Re: Building a Virtual Machine Inside ChatGPT

#679

Post by c7DJTLrn » Sun, Dec 04, 2022, 9:51 AM UTC

This thing is fucking scary. As if everything before it wasn't scary enough.

Re: Building a Virtual Machine Inside ChatGPT

#680

Post by npwr » Sun, Dec 04, 2022, 9:57 AM UTC

alcover wrote: post #668

crucialfelix wrote: post #630

Earlier quoted context omitted.

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.

Last year around the same time I figured that most of the content we read on social networks could be generated by advanced langage models. I then proceeded to research these models and gathered data on the agents in the various networks.

I stopped sleeping altogether, bought a ton of hardware and became delirious. I have now been diagnosed with bipolar disorder. Some psychiatrists have classified my intuitions about langage models usages as "delirious mania". Some think I'm right - but manic nonetheless.

Terribly shitty situation.