Building a Virtual Machine Inside ChatGPT

Post by kgc » Sun, Dec 04, 2022, 4:28 PM UTC

visarga wrote: post #214

quickthrower2 wrote: post #139

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.

> If the generated text included further links to learn more it would be awesome. A new type of language model has been developed that takes a query as input and produces document IDs as output, similar to how Google works, but without relying on an inverted index of keywords. This model can be used on any text to obtain the most relevant references.

Post by jameshart » Sun, Dec 04, 2022, 4:47 PM UTC

johnfn wrote: post #21

Well, I couldn't resist: > {create a script called hn.py that will print out the top 10 posts on hacker news} [a lot of output] > python hn.py 1: Apple acquires Tesla 2: Amazon to open 10,000 brick-and-mortar stores 3: Google unveils new AI technology 4: Facebook to launch new virtual reality headset 5: Microsoft announces new partnership with SpaceX 6: Uber introduces flying cars 7: Twitter to double character limit…

    Traceback (most recent call last):
      File "hn.py", line 1, in 
        import requests
    ImportError: No module named requests

    Collecting requests
      Using cached requests-2.25.1-py2.py3-none-any.whl (61 kB)
    Collecting idna=2.5
      Using cached idna-2.10-py2.py3-none-any.whl (58 kB)
    Collecting urllib3!=1.25.0,!=1.25.1,=1.21.1
      Using cached urllib3-1.25.10-py2.py3-none-any.whl (127 kB)
    Collecting chardet=3.0.2
      Using cached chardet-3.0.4-py2.py3-none-any.whl (133 kB)
    Collecting certifi>=2017.4.17
      Using cached certifi-2020.12.5-py2.py3-none-any.whl (157 kB)
    Installing collected packages: idna, urllib3, chardet, certifi, requests
    Successfully installed certifi-2020.12.5 chardet-3.0.4 idna-2.10 requests-2.25.1 urllib3-1.25.10

    1. Understanding the HN Algorithm
    2. Show HN: A tiny JavaScript library for creating HTML5 presentations
    3. Ask HN: How do you learn a new programming language?
    4. HN is hiring: Software Engineer (Remote)
    5. HN Hackathon 2021: Build the Future of the Open Web
    6. A new HN user's first impressions
    7. How to get started with HN?
    8. A beginner's guide to HN
    9. HN's top posts this week
    10. The best HN threads of all time

    import requests
    
    url = "https://hacker-news.firebaseio.com/v0/topstories.json"
    
    response = requests.get(url)
    
    top_stories = response.json()

    for story_id in top_stories[:10]:
        story_url = f"https://hacker-news.firebaseio.com/v0/item/{story_id}.json"
        story_response = requests.get(story_url)
        story_data = story_response.json()
        print(f"{story_data['title']}")

Post by Aeolun » Sun, Dec 04, 2022, 4:51 PM UTC

moffkalast wrote: post #721

Aeolun wrote: post #710

Earlier quoted context omitted.

> Can anyone please explain to me why this isn't as wildly groundbreaking as this seems? It’s really hard to utilize if the results aren’t consistent.

Well humans are inconsistent and we seem to be utilized reasonably well.

Post by ericpauley » Sun, Dec 04, 2022, 5:26 PM UTC

SeanAnderson wrote: post #828

ericpauley wrote: post #809

Earlier quoted context omitted.

You misunderstand my point, see ggp. What I'm saying is that claims that OpenAI has "locked down" the model are likely due to this noise.

No. I believe you're mistaken. I spoke to ChatGPT for about six hours yesterday and feel that I developed a decent understanding of how to communicate properly with it. It definitely evolved over the course of the day. When I went to bed I was struggling to jailbreak but in the morning I had multiple options that worked first try.

Post by rolph » Sun, Dec 04, 2022, 5:35 PM UTC

numbsafari wrote: post #281

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…

I wonder, if you ask it to write the code for ChatGPT, will it output all of its own code?