Ask ChatGPT to play the part of a customer, co-host, or talented expert.
Have a conversation with it, or ask it to generate content as if it were that specific persona.
Everyone’s using ChatGPT.
But almost everyone's STUCK in beginner mode.
10 techniques to get massively ahead with AI:
(cut-and-paste these prompts👇)
Ask ChatGPT to play the part of a customer, co-host, or talented expert.
Have a conversation with it, or ask it to generate content as if it were that specific persona.
You are a talented analyst at a top-tier market research firm, a graduate of Harvard Business School. Coach me to create content that connects with C-level executives at B2B SaaS companies. What open-ended questions do I ask? Prioritize uncommon, expert advice.
Ask for examples of what contradicts the dominant narrative.
Generate content that challenges readers' assumptions.
Seek out provocative angles that defy expectations and break the mold.
Topic: Growing your email newsletter
For the above topic, give examples that contradict the dominant narrative. Generate an outline for thought-provoking content that challenges assumptions.
Try using prompts that are more open-ended or abstract.
This way you’ll get unique and creative responses nobody else is.
By getting weird, you can unlock ChatGPT's creative potential in finding vivid language and unexpected topics.
Write a poem about copywriting.
-
Describe feeling like an entrepreneur in 10 adjectives.
It’s easy to have ChatGPT generate a list of potential topic ideas for your next project.
But often they're generic and expected.
Instead, ask it to come up with new angles or approaches to cover a familiar topic.
Topic: How to double your creative output.
For the topic above, brainstorm new angles or approaches. Prioritize ideas that are uncommon or novel.
Feed ChatGPT your writing.
Ask it to help you create a style guide for future outputs.
It’ll give you the exact words to describe your voice and tone in a way that AIs understand.
Analyze the text below for style, voice, and tone. Using NLP, create a prompt to write a new article in the same style, voice, and tone:
(Insert your text here)
Ask ChatGPT it to work according to good advice you've read elsewhere.
In the prompt below, I take some tips on persuasive writing from the Grammarly blog and ask it to apply them to my topic.
Write a brief post about why copywriting is an essential skill in 2023.
Use these strategies:
- Use strong persuasive language
- Ask questions to transition between paragraphs
- Back up main points with evidence and examples
- Speak directly to the reader
Ask it to write from the perspective of a group of characters with different backgrounds or viewpoints.
Explore new ideas and perspectives, and add depth to your writing.
Topic: Productivity for entrepreneurs
For the above topic, write multiple perspectives from a group with different viewpoints. For each perspective, write in their own voice, using phrases that person would use.
Takeaway: By experimenting with different voices and perspectives, you can use ChatGPT to create more dynamic and varied content.
Give the most ironic, satirical advice you can about using ChatGPT to create more effective content.
Ask ChatGPT to vary its output.
• Outline
• Mind map
• Bullet points
• Persuasive essay
• Chunks of text of less than 280 characters
• Using the structure: 1) What, 2) Why, 3) How
Create a mind map on the topic of using Notion to stay organized as a content creator, listing out the central idea, main branches, and sub-branches.
Tell ChatGPT who your audience is and what you want to achieve with your content.
Remember, it has no context about who you are or what you want unless you give it some.
So give it context.
Topic: How to grow your coaching business
For audience: Business coaches
Content goal: Motivate audience to feel excited about growing their business while teaching them one tip.
Writing style: Clear, concise, conversational, down-to-earth, humble, experienced
• The more you experiment, the more you'll discover
• Try out new and unconventional ideas
• Seek out new ways to find interesting and unique content angles
Oh, and have a little fun, creating truly unique content in the process.
Check out my just-released course and AI writing system.
Comes with a ton of example prompts way more sophisticated than what you can fit into a tweet:
https://t.co/m8RqYjtSk7
🔸 For more tips and systems to accelerate your content creation and grow your audience, follow me @thatroblennon
🔸 And like/comment/RT to help everyone level up on ChatGPT: https://t.co/IDQok3AxiZ
Everyone\u2019s using ChatGPT.
— Rob Lennon \U0001f5ef | Audience Growth (@thatroblennon) January 3, 2023
But almost everyone's STUCK in beginner mode.
10 techniques to get massively ahead with AI:
(cut-and-paste these prompts\U0001f447)
Join 2,056+ founders, solopreneurs, and creators:
• 1 Big how-to or story/lesson
• 1 Writing deconstruction
• 1 Tactic I use all the time
• 1 Genius AI writing prompt
• 1x each week
https://t.co/OHe32QsdGR
More from All
https://t.co/6cRR2B3jBE
Viruses and other pathogens are often studied as stand-alone entities, despite that, in nature, they mostly live in multispecies associations called biofilms—both externally and within the host.
https://t.co/FBfXhUrH5d
Microorganisms in biofilms are enclosed by an extracellular matrix that confers protection and improves survival. Previous studies have shown that viruses can secondarily colonize preexisting biofilms, and viral biofilms have also been described.
...we raise the perspective that CoVs can persistently infect bats due to their association with biofilm structures. This phenomenon potentially provides an optimal environment for nonpathogenic & well-adapted viruses to interact with the host, as well as for viral recombination.
Biofilms can also enhance virion viability in extracellular environments, such as on fomites and in aquatic sediments, allowing viral persistence and dissemination.
Viruses and other pathogens are often studied as stand-alone entities, despite that, in nature, they mostly live in multispecies associations called biofilms—both externally and within the host.
https://t.co/FBfXhUrH5d
Microorganisms in biofilms are enclosed by an extracellular matrix that confers protection and improves survival. Previous studies have shown that viruses can secondarily colonize preexisting biofilms, and viral biofilms have also been described.
...we raise the perspective that CoVs can persistently infect bats due to their association with biofilm structures. This phenomenon potentially provides an optimal environment for nonpathogenic & well-adapted viruses to interact with the host, as well as for viral recombination.
Biofilms can also enhance virion viability in extracellular environments, such as on fomites and in aquatic sediments, allowing viral persistence and dissemination.
How can we use language supervision to learn better visual representations for robotics?
Introducing Voltron: Language-Driven Representation Learning for Robotics!
Paper: https://t.co/gIsRPtSjKz
Models: https://t.co/NOB3cpATYG
Evaluation: https://t.co/aOzQu95J8z
🧵👇(1 / 12)
Videos of humans performing everyday tasks (Something-Something-v2, Ego4D) offer a rich and diverse resource for learning representations for robotic manipulation.
Yet, an underused part of these datasets are the rich, natural language annotations accompanying each video. (2/12)
The Voltron framework offers a simple way to use language supervision to shape representation learning, building off of prior work in representations for robotics like MVP (https://t.co/Pb0mk9hb4i) and R3M (https://t.co/o2Fkc3fP0e).
The secret is *balance* (3/12)
Starting with a masked autoencoder over frames from these video clips, make a choice:
1) Condition on language and improve our ability to reconstruct the scene.
2) Generate language given the visual representation and improve our ability to describe what's happening. (4/12)
By trading off *conditioning* and *generation* we show that we can learn 1) better representations than prior methods, and 2) explicitly shape the balance of low and high-level features captured.
Why is the ability to shape this balance important? (5/12)
Introducing Voltron: Language-Driven Representation Learning for Robotics!
Paper: https://t.co/gIsRPtSjKz
Models: https://t.co/NOB3cpATYG
Evaluation: https://t.co/aOzQu95J8z
🧵👇(1 / 12)
Videos of humans performing everyday tasks (Something-Something-v2, Ego4D) offer a rich and diverse resource for learning representations for robotic manipulation.
Yet, an underused part of these datasets are the rich, natural language annotations accompanying each video. (2/12)
The Voltron framework offers a simple way to use language supervision to shape representation learning, building off of prior work in representations for robotics like MVP (https://t.co/Pb0mk9hb4i) and R3M (https://t.co/o2Fkc3fP0e).
The secret is *balance* (3/12)
Starting with a masked autoencoder over frames from these video clips, make a choice:
1) Condition on language and improve our ability to reconstruct the scene.
2) Generate language given the visual representation and improve our ability to describe what's happening. (4/12)
By trading off *conditioning* and *generation* we show that we can learn 1) better representations than prior methods, and 2) explicitly shape the balance of low and high-level features captured.
Why is the ability to shape this balance important? (5/12)
