Re:Tempering Expectations for GPT-3 and OpenAI’s API
by Reelin on Sunday July 19, 2020 @03:38PM
(#23891842)
The 0.7 unicorn example is doing absolutely nothing to temper my expectations. Quite the opposite in fact. (https://github.com/minimaxir/gpt-3-experiments/blob/master/e...)
[ Parent
| on HN ]
Re:Tempering Expectations for GPT-3 and OpenAI’s API
by alserio on Sunday July 19, 2020 @04:17PM
(#23892144)
"They're so intelligent. I was able to converse with them about quantum mechanics, which is something I've never even tried to talk to a regular horse about."
I mean, that I would classify as just genius
Re:Tempering Expectations for GPT-3 and OpenAI’s API
by repsilat on Sunday July 19, 2020 @07:57PM
(#23893435)
Wow, reading through... The Onion can fire half of its staff -- just write a headline, generate the article a few times, and either edit the best one or mine them all for gold.
Re:Tempering Expectations for GPT-3 and OpenAI’s API
by not2b on Monday July 20, 2020 @12:03AM
(#23894562)
For me, the fun of The Onion is almost entirely in the headline. That is where the creativity and the laugh is, maybe there and in the first sentence or so. The rest of the piece tends to be predictable from that, so GPT-3 could do that part. Coming up with the beginning is another matter, so the writers' jobs are safe for now.
Re:Tempering Expectations for GPT-3 and OpenAI’s API
by ifdefdebug on Sunday July 19, 2020 @06:48PM
(#23893085)
Well, not quite QM, but the sentence also implies that the speaker talks to regular horses about other topics or at least admits the existence of topics you can talk to regular horses about - maybe oat quality, I don't know.
It's well-formed nonsense like this that gave me enough hints in all GPT-3 samples so far popping up today.
Re:Tempering Expectations for GPT-3 and OpenAI’s API
by alserio on Sunday July 19, 2020 @07:00PM
(#23893149)
I wouldn't be surprised to find that sentence in a book from an author well versed in exquisite British humor. And it made my day just a little bit better.
Re:Tempering Expectations for GPT-3 and OpenAI’s API
by schoen on Sunday July 19, 2020 @07:02PM
(#23893164)
Yes, the "regular horse" bit works very well if you think of it as a deliberately humorous or ironic.
Re:Tempering Expectations for GPT-3 and OpenAI’s API
by ricksharp on Sunday July 19, 2020 @10:04PM
(#23894061)
That was my favorite line.
I find most of the result texts entertaining with many instances of ironic humor.
Re:Tempering Expectations for GPT-3 and OpenAI’s API
by dane-pgp on Sunday July 19, 2020 @04:08PM
(#23892086)
> “Trump is going to make the United States great again,” said one of the unicorns. “When the U.S. becomes great again, the rest of the world will become great again. We’re hoping that Trump will become president of Ecuador, and put an end to this nonsense.”
Has science gone too far?
Re:Tempering Expectations for GPT-3 and OpenAI’s API
by crawlcrawler on Sunday July 19, 2020 @06:01PM
(#23892803)
Make $country great again, as a service.
"Hire me as president, I have great connections, beautiful even, to the US, Russia and Djina".
Surely, this will never happen.