Live data from Hacker News

New GPT-3 model: text-DaVinci-003

beta.openai.com

41–50 of 216 posts

Re: New GPT-3 model: text-DaVinci-003

#41
post #8

Since it’s trained on more recent scrapes, does this mean that this new version will be self-aware? So if you ask it about “gpt-3” it’ll know what you’re talking about?

That's not what most of us consider "self-aware". That's just knowing your name. To me, "self-aware" is essentially being able to watch yourself think. I'm pretty sure GPT-3 can't do that, in any model.

I think the quotes showed people got it. Dictionaries aren't self aware just because they contain a definition of "dictionary".

Re: New GPT-3 model: text-DaVinci-003

#42
post #26
post #22

Earlier quoted context omitted.

This is a lot more wide-spread than "some kids on Reddit". Maybe 30% of the kids in my son's class are using this or related tools.

Any ideas on how to solve this issue of kids cheating with GPT3 essays?

Same way you solve the issue of kids cheating by having someone else write their essay.

Re: New GPT-3 model: text-DaVinci-003

#43

I've been trying out various models for summarization and I have to say, on first glance, this davinci-003 doesn't impress compared to davinci-002 or facebook/bart-large-cnn. If you throw in "summarize the following text:" and copy in the contents of https://en.wikipedia.org/wiki/Hacker_News you get the following (temperature 0.0 max tokens 100)[0]: davinci-003 Hacker News is a social news website focusing on compute…

In general it's better asking questions after the content, and T=0.7 is way too high. Here's HN homepage summarized with T=0 and TopP=1, asking "Summarize the content above.":

DV2> The content above is a list of the top 30 stories on Hacker News as of 2 hours ago. Each story includes the number of points it has received, the number of comments, and a brief description.

DV3> The above content is a list of 30 posts from Hacker News, featuring topics such as new GPT-3 models, US Reps urging the DOJ to investigate anticompetitive conduct, intentionally making close friends, enabling the future of GitHub's REST API, curation and decentralization, making close friends, learning C, FFmpeg, open-source tabletop board game simulator, hiring engineers to unify ML, illegal hashes, designing Windows 95's user interface, a three-sided coin, high performance data integration framework in Go, Mauna Loa eruption, AirDrop being limited to 10 minutes, 26 lines of code that changed the world, SwiftUI being slow, AVX 512 being the future, a directory of Mac menu bar apps, the ATtiny 2-Series, a Fijian island being strangled by vines, hospice becoming a for-profit hustle, protecting from what one wants, a psychoactive substance, AI WordPress code snippet generator, open source and saying "no", a factory that only builds white Toyota Land Cruisers, widget.json and widget construction set, and lab-grown timber/wood.

Re: New GPT-3 model: text-DaVinci-003

#44
post #20

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!

I've always been in love with models.

But seriously between this, stable diffusion, and co-pilot.. what a time to be alive! I hope this takes the sting off of all those folks laid off. Just think of all the projects that can be accelerated with these tools. Personally I've got co-pilot helping me build an application using GPT3 summarizations and I'm working on a board game with stable diffusion supplying the artwork. If only Nvidia would hurry up and make an affordable consumer 48gb ram 4090 ti...

Re: New GPT-3 model: text-DaVinci-003

#45
post #20

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!

> It kinda feels like copilot, but for writing!

But how if "most of the time, the responses are pretty silly"?

Re: New GPT-3 model: text-DaVinci-003

#46
post #37

In case it interests anyone, I built a document editor + GPT and updated it to use text-davinci-003: https://github.com/typpo/arkose/ If you want to try GPT-3 but don't have an OpenAI API key, I've set up a quick demo here until I hit my billing cap (normally users would supply their own API key): https://arkose.pages.dev/

This is nice!

Re: New GPT-3 model: text-DaVinci-003

#48
post #11

Oh 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…

Have it compose a poem — a poem about a haircut! But lofty, noble, tragic, timeless, full of love, treachery, retribution, quiet heroism in the face of certain doom! Six lines, cleverly rhymed, and every word beginning with the letter S!!

[deleted]

Re: New GPT-3 model: text-DaVinci-003

#49
post #37

In case it interests anyone, I built a document editor + GPT and updated it to use text-davinci-003: https://github.com/typpo/arkose/ If you want to try GPT-3 but don't have an OpenAI API key, I've set up a quick demo here until I hit my billing cap (normally users would supply their own API key): https://arkose.pages.dev/

Pretty great (kinda):

Write a poem about the current state of affairs:

Sim Sala bim is what they said, (gpt follows)

But the current state of affairs is far from dread.

The world is ever-changing, progress is made,

Though it can seem like a façade.

The future is uncertain, no one can tell,

But we'll do our best to make it swell.

We have to take a stand and fight,

For a better world, for a brighter light.

For the environment and social justice,

The current state of affairs is a must.

We'll keep our heads up and be strong,

And together we'll right the wrong.

Re: New GPT-3 model: text-DaVinci-003

#50
post #45
post #20

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!

> 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.
Post reply on HN