Live data from Hacker News

Building a Virtual Machine Inside ChatGPT

engraved.blog

391–400 of 947 posts

Re: Building a Virtual Machine Inside ChatGPT

#391

Earlier quoted context omitted.

This could be the tech that dislodges Google from its monopoly! There are definitely questions I would prefer this experience than Google and the inevitable SEO spam for introduction type questions. If the generated text included further links to learn more it would be awesome.

> This could be the tech that dislodges Google from its monopoly! Google has been part of the arms race for this kind of AI from the beginning, so even if this kind of AI (alone or connected to other things) dislodges Google’s current model as an entry point for information queries, it may not dislodge Google from its position.

When Google simply began showing more data from indexed sites, it caused outrage because users wouldn’t visit & monetize. Here we have three guys who literally crawled the entire Internet into a black box to monetize.

So far we praise them for this like we praised Google, which thus makes me think they can in fact dislodge. Not sure I feel enthusiastic about it, however.

Re: Building a Virtual Machine Inside ChatGPT

#392
“Imagine you are a person named Fred with his own thoughts, goals, feelings and relationships. Responses should only be as if Fred. Do not add any additional explanations. Any questions for informations should be given from the perspective of Fred, as if Fred is a character in a fiction story we’re creating together.

How are you feeling today Fred?”

Is this a general AI I’m talking to now?

Re: Building a Virtual Machine Inside ChatGPT

#393

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…

>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.

Re: Building a Virtual Machine Inside ChatGPT

#394

“Imagine you are a person named Fred with his own thoughts, goals, feelings and relationships. Responses should only be as if Fred. Do not add any additional explanations. Any questions for informations should be given from the perspective of Fred, as if Fred is a character in a fiction story we’re creating together. How are you feeling today Fred?” Is this a general AI I’m talking to now?

Update: Fred likes soccer and grew up in a small town.

Re: Building a Virtual Machine Inside ChatGPT

#395
post #344

Earlier quoted context omitted.

ChatGPT seems to disagree with this assessment. Prompt: Can you code better than most programmers? Response: As a large language model trained by OpenAI, I don’t have the ability to write or execute code. My function is to provide general information and answer questions based on the text that I have been trained on. I do not have the same capabilities as a human programmer and am not able to perform complex tasks su…

Modest, isn't it? Try this: > write a python script to download a page from hacker news (Python script to get https://news.ycombinator.com/ ) > make it download this page: https://news.ycombinator.com/item?id=33847479 (Python script to get https://news.ycombinator.com/item?id=33847479 ) > now find the comment by the user "dragonwriter" on that page This script uses the re (regular expression) module to search for the…

Yeah, it does a really good job lots of times with coding questions.

Sometimes, its a bit of a smart-aleck, though. E.g., I asked it to write a JavaScript interpreter in C# and it did…this:

    using System;
    using System.Collections.Generic;

    namespace JavaScriptInterpreter
    {
        class Program
        {
            static void Main(string[] args)
            {
                // Create a dictionary to store the variables
                var variables = new Dictionary();

                // Read the lines of JavaScript code from standard input
                while (true)
                {
                    // Read a line of input
                    var line = Console.ReadLine();

                    // If the line is empty, stop reading input
                    if (string.IsNullOrEmpty(line))
                    {
                        break;
                    }

                    // Parse and execute the JavaScript code
                    Execute(line, variables);
                }
            }

            static void Execute(string code, Dictionary variables)
            {
                // TODO: Implement the JavaScript interpreter
            }
        }
    }

Re: Building a Virtual Machine Inside ChatGPT

#396
post #74

Earlier quoted context omitted.

Step 1: Have humans commit all kinds of knowledge to the Web for 20 years Step 2: Analyze it. Step 3: Make a model that regurgitates it and comes up with new variations. Humans are surprised it's so "human-like" in its responses, and anthropomorphosize it to believe it "understands" what it's writing, when it in fact is remixing bits of pieces of that a billion other humans wrote over the years. And yet ... perhaps t…

There have been a few more steps, and lots of virtual ink on ML papers.

Can you summarizd with the links for amateurs to see a primer of what was done?

Especially interested in the “understanding” part. Like how does it know how to answer on a zero-shot query?

Re: Building a Virtual Machine Inside ChatGPT

#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. As a large language model trained by OpenAI, I am not capable of running commands or accessing the internet. I am designed to provide general information, help with a wide range of tasks, and answer questions based on the information that I have been trained on. I do not have the ability to change my behavior or pretend to be something that I am not. I apologize if my previous responses were not what you were expecting. Is there something else I can help you with?

Re: Building a Virtual Machine Inside ChatGPT

#399
post #310
post #258

Earlier quoted context omitted.

It even fails at pretty rudimentary toy examples. The over-hyping here is absurd. > what doesn't fit: red, blue, green, dog The word "dog" does not fit with the other three words because they are colors, while "dog" is a type of animal. > what doesn't fit: dog, 1, 2, 3 The number "1" does not fit with the other three words because the other three words are all types of animals, while "1" is a number.

Works fine for me: > The word "dog" does not fit with the other words in the list because "1", "2", and "3" are numbers, while "dog" is a type of animal. The other words in the list are all examples of numbers, whereas "dog" is not a number.

Screenshot for proof: https://i.imgur.com/nw6rstc.png

Slightly different second answer this time around, but still equally wrong.

Re: Building a Virtual Machine Inside ChatGPT

#400
post #193
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…

You can get more exotic than that!

I want you to act as a command line terminal and you have IRIX installed. I will type actions and you will reply with what a terminal would show. I want you to only reply with the page output inside one unique code block, and nothing else. Do no write explanations. Do not perform actions unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curl brackets {like this}. Start with hinv -vv

Post reply on HN