Subscribe to Paragraph to receive new posts directly to your inbox.
We're excited to announce the launch of Paragraph AI, powered by GPT-4.
The world has been captivated by ChatGPT for the past few months, and for good reason. AI is transforming how creators create content, making it easier than ever to generate captivating titles, structured outlines, and even complete posts. Starting today, you can tap into GPT-4, the latest version of OpenAI's powerful language model, natively in Paragraph.
Here's how Paragraph AI can help streamline your writing process:
Title Generation: Struggling with finding the perfect attention-grabbing title? GPT-4 can suggest multiple creative titles based on your input, ensuring you make a lasting impression on your readers.
Outline Creation: Get your thoughts organized in no time. Enter your topic, and GPT-4 will produce a structured outline for your post, allowing you to focus on fleshing out your ideas and creating compelling content.
Full Post Generation: Need a little more help? GPT-4 can generate entire article drafts or blog posts based on your input, offering a solid foundation to build upon or fine-tune as needed.
Say goodbye to writer's block! By harnessing the power of GPT-4, Paragraph AI brings endless possibilities to content creation. Whether you're a seasoned writer in need of a productivity boost or a beginner looking for guidance, you'll be able to craft engaging content like never before.
We'll be integrating AI into more surfaces in the future to empower creators with additional ways to generate & refine their writing.
Ready to get started? Try Paragraph AI today and experience the future of digital storytelling.
This post was generated using Paragraph AI.
Over 2.5k subscribers
Good
Powerful AI
Very cool features! AI is going everywhere!
we love to see it!!
Thanks for your contribution for content creation and user education of AGI. I'm kongsen Young, a writer, coder and startup founder. I write at Paragraph, it's awesome. I used AI in Paragraph to generate ideas. It helped me a lot. find more info at: https://paragraph.xyz/@gyz
Prompt engineering is more challenging than expected. Learned this by building @paragraph. - token length too large so need to preprocess post before summarization - chatGPT does a bad job at estimating characters of it's response so we often hit FC char limits (need retry logic) - often encounters hallucinations
I’ve learned the same about token length. I’m building netbox and have been working on a prototype. Token length is def an issue. Only when building, you realize the bottlenecks of new tech
Btw are you using OpenAI API or just using an open source model? The problem with OpenAI API that I see is that there is no way to control the limit for spending as far as I can tell
I'm using the OpenAI API. They do have monthly spending limits you can enforce. IIRC $100/mo is the default, but we submitted a quota request to bump it
I've been experiencing this last few days... attempting to feed in a SQL database schema and then asking it to generate test data. have to do one table at a time else it hallucinates. eventually starts drifting/hallucinating anways, then needs corrections, then I run out of requests and have to wait a few hours :|
Which model are you seeing hallucinations on? Just getting started building with GPT-4, was hoping it would have fewer hallucinations
GPT4
https://i.imgur.com/zIighZq.jpg