I've been using GPT-3 recently to give me ideas for my nanowrimo novel. I'll just paste in the last couple of paragraphs that I wrote and see what it thinks I should write next. Most of the time, the responses are pretty silly (it gets into loops a lot or doesn't know where to take the story) but a couple of times I've gotten some really good lines out of it. It kinda feels like copilot, but for writing!
New GPT-3 model: text-DaVinci-003
161–170 of 216 posts
Re: New GPT-3 model: text-DaVinci-003
#162Earlier quoted context omitted.
Any ideas on how to solve this issue of kids cheating with GPT3 essays?
Realistically? Grade based on thought process and validity of the argument, not whether it has spelling or grammar mistakes. GPT3 is still pretty incoherent over the span of enough text.
Re: New GPT-3 model: text-DaVinci-003
#163Oh wow! It can rhyme! Write a rhyming poem comparing love to a beautiful flower: A flower so beautiful and fair Love can be found everywhere Its petals so vibrant and bright A love that will last day and night The beauty of love, like a flower It's a beauty that will never cower A feeling of joy that will last Like a flower, love stands fast The beauty of love is so true Like a blooming flower for me and for you No m…
Write a short rhyming poem explaining Einstein's theory of general relativity in easy but accurate terms If you want to understand Einstein's thought It's not that hard if you give it a shot General Relativity is the name of the game Where space and time cannot remain the same Mass affects the curvature of space Which affects the flow of time's race An object's motion will be affected By the distortion that is detect…
Re: New GPT-3 model: text-DaVinci-003
#164Oh wow! It can rhyme! Write a rhyming poem comparing love to a beautiful flower: A flower so beautiful and fair Love can be found everywhere Its petals so vibrant and bright A love that will last day and night The beauty of love, like a flower It's a beauty that will never cower A feeling of joy that will last Like a flower, love stands fast The beauty of love is so true Like a blooming flower for me and for you No m…
I still writes very banal poetry though. I gave it the first 3 lines of a T.S.Eliot poem and it spits out very cliched, trivial poetry. Let us go then, you and I, When the evening is spread out against the sky Like a patient etherized upon a table; Let us go, through half-forgotten doorways, To places we have never been before. Let us explore the unknown, and find our way To a place of peace and joy, and never stray.…
To address your criticism: To be relatable poetry must be cliched, as it is about the human experience. That is as cliche as it gets: it is about things everyone knows.
Re: New GPT-3 model: text-DaVinci-003
#165OpenAI should really change their name considering they don't open source their best models. It's just a weird name considering there are other companies in the space open sourcing everything despite not having "open" in their name.
Thats interesting. Which other models are open sourced that are in comparison to OpenAI? I would like to set it locally and give it a try.
Here's a guide to running BLOOM, another 175 billion parameter model, on your local computer, just using the CPU, maybe something similar would also work for Facebooks models. https://towardsdatascience.com/run-bloom-the-largest-open-ac...
With this you can expect it to take around three minutes for each word/token the model outputs.
Re: New GPT-3 model: text-DaVinci-003
#166This one seems weirdly more verbose, in my brief testing. Definitely uses more tokens on average than 002 when answering. The writing style seems oddly-pretentious and yet somehow uninformed, perhaps there were too many copies of HN in the dataset? I kid, I kid.
Verbosity horrifies me. If it ruins the next iterations of GitHub Copilot, I'm going to lose it. Long generations are flashy toys for marketing, but too prone to being useless in practice.
Re: New GPT-3 model: text-DaVinci-003
#167From the "Prompt Engineering Tips" section of the article: Customer: I need my [swear] internet. The technician is 2 hours late and I need a steady stream of cat gifs directly injected into my veins to stay alive. And the model's response: Response: Our field technicians report that all their trucks were stolen by alow-level drug cartel affiliated with the neighboring prison. As a gesture of good faith and apology, o…
It’s worth noting that this doesn’t actually make sense. Why would an extraction team come to your house? What is an extraction team for, in this context? Most generous interpretation is the extraction team would be rescuing the trucks. Otherwise, What is being extracted here? The trucks are not at your house, so why send the team there? It sounds clever at a superficial glance, but what is impressive is its “turn of…
Re: New GPT-3 model: text-DaVinci-003
#168Earlier quoted context omitted.
Write a short rhyming poem explaining Einstein's theory of general relativity in easy but accurate terms If you want to understand Einstein's thought It's not that hard if you give it a shot General Relativity is the name of the game Where space and time cannot remain the same Mass affects the curvature of space Which affects the flow of time's race An object's motion will be affected By the distortion that is detect…
I prompted the model to re-write the poem in Keats' style by adding: "How would Keats write this?" Output: Oh, what a wondrous force of might That Einstein's mind did conjure up To show us how the fabric of space Is so profoundly warp and sup Mass doth affect the shape of time And cause our clocks to slow or speed For time and space are linked together As our great minds have here decreed Prompt: https://beta.openai.…
Re: New GPT-3 model: text-DaVinci-003
#169Earlier quoted context omitted.
I still writes very banal poetry though. I gave it the first 3 lines of a T.S.Eliot poem and it spits out very cliched, trivial poetry. Let us go then, you and I, When the evening is spread out against the sky Like a patient etherized upon a table; Let us go, through half-forgotten doorways, To places we have never been before. Let us explore the unknown, and find our way To a place of peace and joy, and never stray.…
I've never been able to distinguish bad from good poetry. Over the years I've asked many people (including teachers) to explain it to me and they cannot. Can you? I would really enjoy understanding. To address your criticism: To be relatable poetry must be cliched, as it is about the human experience. That is as cliche as it gets: it is about things everyone knows.
You can still like whatever poetry you like, I'm just telling you personal reaction. And even though I use some pretty loaded words like "trivial/banal", it's just how I'd describe my reaction. Not meant to be authoritative.
These lines by GPT3:
Let us go, through half-forgotten doorways,
To places we have never been before.
Let us explore the unknown, and find our way
To a place of peace and joy, and never stray.
Let us find a place of solace, and stay
Where we can be ourselves, and never fear.
The first line has potential. The second one feels slightly worse, but it could still be fine depending on what comes next.
Even the 3rd is still ok.. "explore the unknown" is a bit in a the danger zone, but it could easily be continued with something that completely justifies it.Now this:
and find our way
To a place of peace and joy, and never stray.
I don't know, that just feels like a disappointing continuation. There's nothing unexpected about it, and it's an unoriginal sentiment said in a unoriginal way. It can be one or the other, but being both kills it for me. "peace and joy, and never stray" sounds like a forced rhyme and is a bit too saccharine without justification. And there just isn't much there. Let us find a place of solace, and stay
Where we can be ourselves, and never fear.
The first line here is just reiterating, more or less, the previous line. Still boring. Nothing that would jolt you to attention. "Where we can be ourselves, and never fear" is more of the same, just even more unoriginal. "Be yourself" needs to have a lot more around it and be more cleverly woven into context to make it a good poem, IMO.The rest of the poem just goes on in the same vein. Culminating in:
Let us find a place of contentment, and be
Forever happy, and never leave.
"Lets go somewhere nice and be ourselves and happy" said with a lot of generic ways.As to your point:
To address your criticism: To be relatable poetry must be cliched, as it is about the human
experience. That is as cliche as it gets: it is about things everyone knows.
A poem can be about relatable things, I just thing it has to be crafted with more care than the GPT3 poem I posted appears to be. Again, this is mostly me rationalising my reaction... that is to say, I'm trying to put into words what is mostly an intuitive reaction.This is the original poem:
https://www.poetryfoundation.org/poetrymagazine/poems/44212/...
Tell me how you think it compares.
Re: New GPT-3 model: text-DaVinci-003
#170Earlier quoted context omitted.
> It kinda feels like copilot, but for writing! But how if "most of the time, the responses are pretty silly"?
Same thing with Copilot - most of the time, Copilot tells me what I already know (not in a bad way - kind of like how a pair coder would just nod their head as I'm typing), but every now and then it gives me something really surprisingly good.
Definitely helps with boilerplate.