ChatGPT Got Some Things Wrong About Paragraph

avatar

If you haven’t seen it yet, on April 6, I posted ++a Twitter thread++ comparing Web3 publishing platforms Paragraph and Mirror.

What you may not realize is that I created that Twitter thread with the assistance of ChatGPT.

It’s not that I needed to do so, but I wanted to experiment with ChatGPT and it was the perfect opportunity to take the AI chat program for a test drive to discover its true capabilities. I’ve got to say, though I’m late to the party, I am a little bit impressed.

I started with a simple question: Compare Mirror and Paragraph.

The program began with Mirror. Its description of Mirror was pretty accurate.

I was not, however, impressed with the description of Paragraph. It got some fundamental facts wrong.

Because Paragraph allows newsletter creators to token-gate their content, I knew the part about not using blockchain technology was incorrect. Furthermore, it isn’t just for serialized fiction. I asked a follow-up question:

I'm sorry. I must have miscommunicated. I meant Paragraph.xyz.

Here is the first half of ChatGPT’s response:

And ChatGPT followed that up with:

Not bad, but it still says Paragraph is for serialized fiction. I’m not sure why the platform is described that way. Maybe it does host a lot of serialized fiction.

The final summary paragraph of ChatGPT’s response reads:

Curious about whether Paragraph’s newsletters can be used to publish non-fiction content, I asked:

Can Paragraph be used to publish newsletters focused on non-fiction content?

Here was the response:

Finally, I got around to asking ChatGPT to compare Mirror and Paragraph as if writing a Twitter thread. Here’s what I got:

ChatGPT’s written response, in full, is verbatim below:

Sure, here's a Twitter thread comparing Mirror and Paragraph:
1/5: Mirror and Paragraph are both blockchain-based publishing platforms that offer creators new ways to share and monetize their work.
2/5: Mirror focuses on long-form, serialized content like essays and books, while Paragraph specializes in serialized fiction.
3/5: Both platforms allow creators to publish their work in a decentralized way, without intermediaries, and receive support directly from their readers.
4/5: However, Mirror uses cryptocurrency incentives to promote high-quality content, while Paragraph operates on a subscription model where readers pay a monthly fee to access all the content on the platform.
5/5: Whether you're a writer, artist, or content creator, both Mirror and Paragraph offer exciting new ways to share and monetize your work. Check them out and see which one is right for you! #blockchain #publishing #creativity

Not bad, but why only 5 tweets? I really wanted something longer. I asked ChatGPT another question:

Is it possible to embed NFTs in Mirror or Paragraph posts?

Of course, I knew the answer to that question, but I wanted to see what ChatGPT would say and, if I liked the answer, I could incorporate it into my Twitter thread. Here’s the response:

The final paragraph of ChatGPT’s response was:

Overall, the use of NFTs in publishing is still relatively new and evolving. However, both Mirror and Paragraph have shown a willingness to experiment with new technologies and explore new ways to support and reward creators, so it's likely that we will see more integration of NFTs and other blockchain-based features in the future.

Satisfied with that answer, I asked the program to incorporate that response into our Twitter thread. Again, I only got five tweets. Here’s the updated thread:

I was fairly happy with the response, but I wanted a longer Twitter thread, so I combined the two Twitter threads on my own to create a unique, original Twitter thread comparing Mirror and Paragraph as Web3 publishing platforms. You can ++read the Twitter thread right here++.

If you haven’t already done so, please take ++my survey regarding Paragraph and Substack++.

If you like Cryptocracy, I’d be delighted if you’d share it with your friends and subscribe. To subscribe at Paragraph, ++click here++. At Mirror, ++click here++. At Substack, click here.

First published at Substack.



0
0
0.000
0 comments