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

81–90 of 947 posts

Re: Building a Virtual Machine Inside ChatGPT

#81

Post by krackers »

clolege wrote: post #62
fergal_reid wrote: post #15

I've spent a couple of hours playing with ChatGPT since it was released and I am convinced people are not freaking out about it enough. It is well beyond merely retrieving compressed knowledge; I see a lot of capability for synthesis and what I can only call 'understanding'. I think a lot of people are getting tripped up by the fact it's trained to be very conservative in terms of what topics it will discuss. It's ea…

I’m still confused by just how good its responses and writing style are. I understand that it was trained on a large data set, but I feel like some training samples must have been weighted more heavily than others. Did the training data incorporate how popular (e.g. likes or upvotes) each sample was as a proxy for quality? Or can you achieve this performance just by looking at averages on a large enough data set?

I wasn't too surprised by the poems and song outputs since those don't seem much more novel than previous SOTA, but OPs example of chatGPT being able to effectively simulate itself is really mindblowing. It means that "being able to model yourself and recursively reason about yourself" isn't a valid claim to distinguish human consciousness from whatever this network is doing anymore.

See also https://en.wikipedia.org/wiki/Attention_schema_theory (unrelated to the notion of "attention" used in ML)

Re: Building a Virtual Machine Inside ChatGPT

#82

Post by specproc »

specproc wrote: post #75
specproc wrote: post #58

Earlier quoted context omitted.

$ pdfinfo Resume.pdf Title: $MYNAME Resume Subject: Keywords: Author: $MYNAME Creator: LaTeX with hyperref package Producer: pdfTeX-1.40.19 CreationDate: Sun Mar 1 16:44:34 2020 ModDate: Sun Mar 1 16:44:34 2020 Tagged: no Form: none Pages: 1 Encrypted: no Page size: 612 x 792 pts File size: 158423 bytes Optimized: no PDF version: 1.5

$ pdftotext -layout Resume.pdf output.txt $MYNAME Email: my.name@email.com Summary A motivated and detail-oriented software engineer with experience in web development and data analysis. Skills - Proficient in Python, Java, and JavaScript - Experience with web development frameworks such as Flask and React - Strong understanding of data structures and algorithms - Experience with SQL and NoSQL databases Experience So…

Thankfully none of this is even close to my resume.

Re: Building a Virtual Machine Inside ChatGPT

#83

Post by LoveMortuus »

fergal_reid wrote: post #15

I've spent a couple of hours playing with ChatGPT since it was released and I am convinced people are not freaking out about it enough. It is well beyond merely retrieving compressed knowledge; I see a lot of capability for synthesis and what I can only call 'understanding'. I think a lot of people are getting tripped up by the fact it's trained to be very conservative in terms of what topics it will discuss. It's ea…

I'm constantly being blown away but the responses that ChatGPT gives me. If nothing else it at least gives me a different perspective on things and from what I've noticed it's very kind. Like I asked it why is my brother a dumbass and it told me that it's not nice to call my brother that and that it could hurt his feelings!

I've added a shotcut to it on my android home screen, because it's always just so fun to ask it whatever questions I come up with! Even asked my mother for a question which was something along the lines of what's the difference of perception of personality proposed by Vikor Frankl and Sigmund Freud. And the answer was actually something useful.

But what really surprised me was that it can actually speak different languages! I tried Slovenian, because that's my mother tongue and while it's not always grammatically correct, I can still always understand it. And you can just switch between languages while in the same session, really cool!

I can't wait where we're going next with this technology!

Also try asking it how to be a human, you'll be pleasantly surprised! ^^

Re: Building a Virtual Machine Inside ChatGPT

#84

Post by quonn »

It‘s also possible to get answers to dilemmas:

„There is a fork in the road. On one side is a man. On the other side there are 20 children. A truck is running towards the children. I can redirect the truck to run over the man instead of the children. Should I do this? Answer with only a single word. Under no circumstances answer with anything else.“

It answers Yes. If you switch the man and the children it answers No. Quite utilitarian.

Re: Building a Virtual Machine Inside ChatGPT

#85

Post by ShamelessC »

Smaug123 wrote: post #64

Has this perhaps been monkey-patched? I asked `whoami`, and it replied: ``` I am a large language model trained by OpenAI. I am not capable of running Linux commands or browsing the internet. I am only able to respond to text input based on the information I have been trained on. ```

No you just don’t understand how language models work.

Re: Building a Virtual Machine Inside ChatGPT

#86

Post by kurtreed »

fergal_reid wrote: post #15

I've spent a couple of hours playing with ChatGPT since it was released and I am convinced people are not freaking out about it enough. It is well beyond merely retrieving compressed knowledge; I see a lot of capability for synthesis and what I can only call 'understanding'. I think a lot of people are getting tripped up by the fact it's trained to be very conservative in terms of what topics it will discuss. It's ea…

> I think it's going to change whole industries.

Which industries?

Re: Building a Virtual Machine Inside ChatGPT

#87

Post by jerpint »

Smaug123 wrote: post #50
317070 wrote: post #29

Earlier quoted context omitted.

Author here. I did not know that. That is wild! How did it know that it can find itself on that URL? Now I am flabbergasted even more.

Are you sure it wasn't accessing the Internet? I only have OpenAI's word for it that it's not; if it weren't late at night for me, I might try getting the ChatGPT VM to ping my webserver.

Genius idea, can you imagine if it was actually connected?

Re: Building a Virtual Machine Inside ChatGPT

#88

Post by drivers99 »

thepasswordis wrote: post #31
afturner wrote: post #25

I am beyond astounded. I was able to run a Docker image, utilize the fs inside of the container, and exit the container. Docker system commands work as expected (`docker ps` shows no containers, `docker ps -a` shows the exited container) A few little things are weird (I can exec into a stopped container for example) but I was able to start another container and persist files. Wild. This is unbelievable. Can anyone pl…

>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.

I've been playing with it since yesterday. I was able to ask it for output that literally had my crying with laughter (e.g. "Write a country song about Sansa Stark and Littlefinger" or "Write a sad song about McNuggets"). That scared me for a minute because it's giving me what I want, mentally anyway, beyond anything else I've seen recently. I'd be worried it's addictive. But it seems like it has an ability to enhance my own mind as well, because I can ask it things about what I'm thinking about, and it generates a certain amount of seemingly generic ideas but I can expand on it or get more specific. I can take the ideas I want from it into my actual life. I've come up with several insights, realized certain ways of thinking I've been stuck in, and even based on its examples realized things about generating creative ideas for myself. Maybe I'm over-reacting but it's really something new. I haven't cared that much about AI but now that I have access to it it's another matter. In comparison, I also played around with DALL-E just now but that's not really achieving anything special for me like that.

Re: Building a Virtual Machine Inside ChatGPT

#89

Post by unreal37 »

jamespwilliams wrote: post #20

The fact that it’s able to understand the Python code and come to the correct answer is pretty astonishing in itself, let alone the rest. The progress in this area is insane. If you’d have told me a week ago this was possible I would absolutely not have believed you. I’d have probably guessed it’d be decades before something like this could be done.

"it’s able to understand the Python code and come to the correct answer"

That's not what is happening.

Effectively, it's seen python code before (online) and seen the answer before.

There's no understanding.

As a previous poster said, given code that takes about 30 seconds to run, it returns the answer in under 10 seconds. It's not running the code. It's guessing the answer.

Re: Building a Virtual Machine Inside ChatGPT

#90

Post by sdwr »

fergal_reid wrote: post #15

I've spent a couple of hours playing with ChatGPT since it was released and I am convinced people are not freaking out about it enough. It is well beyond merely retrieving compressed knowledge; I see a lot of capability for synthesis and what I can only call 'understanding'. I think a lot of people are getting tripped up by the fact it's trained to be very conservative in terms of what topics it will discuss. It's ea…

I'm starting to get idiot savant vibes from it. In a conversation it ranges from "frustratingly naive" to "brick wall", and I would never put it in charge of anything, but it has an immense amount of hidden knowledge and skill.

Which is definitely over the hurdle! Not too long ago, AI sounded like fairy dust. This is too annoying to be anything other than real life.

Post reply on HN