Everyones using ChatGPT for content writing. Meanwhile Claude is quietly outperforming it on every platform.
I switched 3 months ago and my engagement jumped 340% across all socials.
The secret isnt Claude itself. Its the 10 prompts that make it write like an actual human, not a corporate robot.
Here they are: 🧵
I switched 3 months ago and my engagement jumped 340% across all socials.
The secret isnt Claude itself. Its the 10 prompts that make it write like an actual human, not a corporate robot.
Here they are: 🧵
1. The Coffee Shop Test
Prompt:
"Write this like you're explaining it to a friend over coffee. No marketing speak. No corporate jargon. Just straight talk about [topic]. If it sounds like a LinkedIn post, rewrite it."
Claude actually gets this. ChatGPT still sounds like it's pitching a SaaS product.
Prompt:
"Write this like you're explaining it to a friend over coffee. No marketing speak. No corporate jargon. Just straight talk about [topic]. If it sounds like a LinkedIn post, rewrite it."
Claude actually gets this. ChatGPT still sounds like it's pitching a SaaS product.
2. Voice Finder
Prompt:
"Give me 5 different ways to say this same idea. Make each one sound like a different person wrote it - one cynical, one excited, one skeptical, one matter-of-fact, one surprised."
This is how I find MY voice. Pick the version that feels most natural, then Claude refines it.
Prompt:
"Give me 5 different ways to say this same idea. Make each one sound like a different person wrote it - one cynical, one excited, one skeptical, one matter-of-fact, one surprised."
This is how I find MY voice. Pick the version that feels most natural, then Claude refines it.
3. AI Word Assassin
Prompt:
"Rewrite this without any words that appear in typical AI-generated content. Ban these: 'delve', 'crucial', 'leverage', 'landscape', 'robust', 'game-changer'. Use conversational alternatives."
Game. Changer. (see what I did there?)
The difference is night and day.
Prompt:
"Rewrite this without any words that appear in typical AI-generated content. Ban these: 'delve', 'crucial', 'leverage', 'landscape', 'robust', 'game-changer'. Use conversational alternatives."
Game. Changer. (see what I did there?)
The difference is night and day.
4. Twitter Fight Mode
Prompt:
"Write this like you're responding to someone who challenged you on Twitter. Keep it factual but add personality. Show some edge without being aggressive."
My engagement tripled when I stopped sounding like a press release and started sounding like a human with opinions.
Prompt:
"Write this like you're responding to someone who challenged you on Twitter. Keep it factual but add personality. Show some edge without being aggressive."
My engagement tripled when I stopped sounding like a press release and started sounding like a human with opinions.
5. Story Time Formula
Prompt:
"Take this topic and write it like you're telling a story about something that just happened to you. Start with 'This is wild' or 'Holy shit' or 'Okay so'. Make it feel spontaneous."
People engage with stories, not statements. Claude nails this format better than any other AI.
Prompt:
"Take this topic and write it like you're telling a story about something that just happened to you. Start with 'This is wild' or 'Holy shit' or 'Okay so'. Make it feel spontaneous."
People engage with stories, not statements. Claude nails this format better than any other AI.
6. Rhythm Master
Prompt:
"Write this in short, punchy sentences. Max 15 words per sentence. Vary the rhythm - some super short (3-5 words), some medium (8-12 words). Never three long sentences in a row."
Rhythm matters. ChatGPT writes like a textbook. Claude writes like someone who actually understands pacing.
Prompt:
"Write this in short, punchy sentences. Max 15 words per sentence. Vary the rhythm - some super short (3-5 words), some medium (8-12 words). Never three long sentences in a row."
Rhythm matters. ChatGPT writes like a textbook. Claude writes like someone who actually understands pacing.
7. Pattern Interrupt
Prompt:
"Add one unexpected comparison or analogy that makes people stop scrolling. Don't use common comparisons. Make it weird but accurate. Something that makes people think 'huh, never thought of it that way.'"
The best content makes people pause. Claude's analogies actually land instead of feeling forced.
Prompt:
"Add one unexpected comparison or analogy that makes people stop scrolling. Don't use common comparisons. Make it weird but accurate. Something that makes people think 'huh, never thought of it that way.'"
The best content makes people pause. Claude's analogies actually land instead of feeling forced.
8. Fluff Destroyer
Prompt:
"Remove every adjective and adverb that doesn't add new information. If 'very' or 'really' or 'extremely' appears, cut it or replace with a stronger verb. Show, don't tell."
Strong writing doesn't need emphasis markers. ChatGPT loves fluff. Claude respects your reader's time.
Prompt:
"Remove every adjective and adverb that doesn't add new information. If 'very' or 'really' or 'extremely' appears, cut it or replace with a stronger verb. Show, don't tell."
Strong writing doesn't need emphasis markers. ChatGPT loves fluff. Claude respects your reader's time.
9. Contrarian Angle
Prompt:
"Write this like you're contradicting conventional wisdom. Lead with what everyone gets wrong, then explain what's actually true. Make it feel like you're letting someone in on a secret."
Contrarian angles get engagement. People share things that challenge their assumptions.
Prompt:
"Write this like you're contradicting conventional wisdom. Lead with what everyone gets wrong, then explain what's actually true. Make it feel like you're letting someone in on a secret."
Contrarian angles get engagement. People share things that challenge their assumptions.
10. Specificity Machine
Prompt:
"Take this draft and add 3 specific examples or numbers. Replace every vague claim with concrete evidence. If you can't find real data, flag it so I can add it manually."
Specificity = credibility. "Engagement increased" vs "Engagement went up 340%"
See the difference?
Prompt:
"Take this draft and add 3 specific examples or numbers. Replace every vague claim with concrete evidence. If you can't find real data, flag it so I can add it manually."
Specificity = credibility. "Engagement increased" vs "Engagement went up 340%"
See the difference?
The secret isn't the AI you use.
It's how you prompt it.
ChatGPT is trained to be helpful and safe. Claude is trained to actually sound human.
That difference shows up in every single post.
My content stopped sounding like AI the day I switched.
Try these prompts. Thank me later.
It's how you prompt it.
ChatGPT is trained to be helpful and safe. Claude is trained to actually sound human.
That difference shows up in every single post.
My content stopped sounding like AI the day I switched.
Try these prompts. Thank me later.
As always, Thank you for reading this.
If you enjoyed this post:
1. Follow me @hasantoxr for more of these
2. RT the tweet below to share this thread with your audience
If you enjoyed this post:
1. Follow me @hasantoxr for more of these
2. RT the tweet below to share this thread with your audience
https://twitter.com/1506055005992026115/status/2019862711585456388
• • •
Missing some Tweet in this thread? You can try to
force a refresh
