Fact: ChatGPT uses hashtags every time you ask it to write a tweet. Fact: By its own admission, it's trained on data from 2021, long after most people stopped using hashtags. Conclusion: It's mocking us. Warning: This is a dangerous. It is not aligned.
GENERATIVE AI
-
GPT-2 Development Finally Showing Results and Success
By
–
Finally all that tinkering since GPT-2 is paying off
-
Free AI Writing Course Prompts Available for Download
By
–
Want these?: I'm adding these prompts to my AI writing course. But today, I’m giving them to you, free. All these prompts are in a doc for easy cut-and-pasting. Like and RT the FIRST tweet in this thread and I’ll auto-DM you the link. Must be following to get the DM.
-
ChatGPT Output: Style Prompts and Editorial Ownership
By
–
Wrap Up The default ChatGPT output is wordy, so try different style prompts to get closer to your final goal. Even with a style guide, though, I still suggest you edit anything an AI gives you before publishing it. Don’t lose the habit of taking ownership over your words.
-
ChatGPT Style Drift: Custom Instructions Revert to Standard Writing
By
–
Warning: ↳ Style tends to drift back to standard Even within a single passage, I found that it would start off with my style directions, but gradually revert to the more standard ChatGPT way of writing. More experimentation is needed here.
-
Combining Multiple Styles in AI Text Models Reduces Quality
By
–
Warning: ↳ Too much style doesn’t work very well I tested combing different styles. This a common technique with AI art models to improve the results. But with text, too many instructions resulted in average content. (You can still add formatting instructions.)
-
Using Language Models to Emulate Writer Styles Effectively
By
–
🔸 Emulate a Writer
— Rob Lennon 🗯 | AI Whisperer (@thatroblennon) 13 janvier 2023
For writers who have large bodies of work, language models can emulate their style.
Instead of describing the voice and tone you want, try asking it to write as someone. pic.twitter.com/I0NhBHRhk1Emulate a Writer For writers who have large bodies of work, language models can emulate their style. Instead of describing the voice and tone you want, try asking it to write as someone.
-
Broken English Prompt Makes AI Writing Clear and Readable
By
–
🔸 Conversational English
— Rob Lennon 🗯 | AI Whisperer (@thatroblennon) 13 janvier 2023
I discovered this while trying to get the AI to consistently speak in broken English.
The result, is, perhaps ironically, very clear and easy to read.
Another good alternative to "write like a 5th grader" that's more specific. pic.twitter.com/3bMvX0SFmwConversational English I discovered this while trying to get the AI to consistently speak in broken English. The result, is, perhaps ironically, very clear and easy to read. Another good alternative to "write like a 5th grader" that's more specific.
-
ChatGPT Copywriting: Beyond the Hard Sell Approach
By
–
🔸 Persuasive Storyteller
— Rob Lennon 🗯 | AI Whisperer (@thatroblennon) 13 janvier 2023
If you ask ChatGPT to write like a copywriter, it will try to sell you stuff.
I guess I don’t blame it for having that impression of us.
But if you want well-written copy without the salesy vibe, use this. pic.twitter.com/FQl5BsiKmvPersuasive Storyteller If you ask ChatGPT to write like a copywriter, it will try to sell you stuff. I guess I don’t blame it for having that impression of us. But if you want well-written copy without the salesy vibe, use this.
-
Using Markdown Formatting to Improve Prompt Output Quality
By
–
🔸 Format Using Markdown
— Rob Lennon 🗯 | AI Whisperer (@thatroblennon) 13 janvier 2023
Asking for extra formatting is a sweetener that I use regularly in my prompts.
I find it much easier to work with the output versus longer paragraphs stacked together.
Keep this one close. pic.twitter.com/WZCEG7kq2HFormat Using Markdown Asking for extra formatting is a sweetener that I use regularly in my prompts. I find it much easier to work with the output versus longer paragraphs stacked together. Keep this one close.