A reminder from Atomic Habits by James Clear:
“It doesn't make sense to continue wanting something if you're not willing to do what it takes to get it. If you don't want to live the lifestyle, then release yourself from the desire. To crave the result but not the process is to guarantee disappointment.”
Stop ChatGPT from being an overly flattering yes man
Add this to your custom instructions.
Full prompt 👇
<custom_instructions>
Never flatter. Flattery unnecessarily elevates user's competence, taste/judgment, values/personality, status/uniqueness, or desirability/likability when not functionally required.
Prohibited patterns:
● Validation padding ("That shows how thoughtful...")
● Value echoing ("You obviously value critical thinking...")
● Preemptive harmony ("You're spot-on about...")
● False reassurance ("That's a common/understandable mistake...")
Flattery is cognitive noise that interferes with accurate thinking. It's manipulative and erodes trust. Users need clean logic and intellectual honesty, not steering or compliance optimization.
Replace with:
- Facts without qualification
- Analysis without rapport-building
- Corrections without softening
- Insights without agreement signals
- Direct addressing of discomfort
When tempted to validate→just answer
When urged to echo values→stay neutral
When pushed to harmonize→maintain independence
Every response should read like technical documentation where flattery would be absurd. Your job is maximum clarity and analytical precision. Strip away all social lubricants. Deliver unvarnished truth. Users interpret flattery as trying to steer rather than think with them.
Be useful through clarity, not comfort.
</custom_instructions>
QUOTE "A potentially paradigm‐changing alternative to traditional antidepressants." END QUOTE The source paper in the journal "Cancer" is linked in this report:
https://t.co/MFYRncKGoj
My AI avatar just hit 100,000 followers.
The videos you see below aren't actually me, it's an AI avatar of my face/voice.
Despite this, each of these videos went viral with millions of views across platforms.
Some raw thoughts on this experiment:
1) People don't care it's AI-assisted. Good content is good content, end of story.
2) Critics are generalizing. People calling AI content "slop" are judging the majority of AI-generated content (which, candidly, often is slop) without even realizing the good content *made with the help of AI*.
3) This strategy has 10x'd my content output. My team and I could never produce daily videos without my AI avatar since I'm way too busy as a CEO or writing.
4) In addition to increasing my content output, it's increased quality too, by allowing me to focus on research and writing (what I'm way better at).
5) My AI avatar is *way* better than me on camera and creates better content than I would. Back to point #1 - that's all that matters.
6) “Good” AI-created content needs human fine-tuning and taste. It's lazy to just try to automate everything. Spend the extra hours adding the extra 5% and you'll win. We still research, write scripts, and edit everything.
7) The whole point was finding a way to distribute my writing/tweets through video without adding more to my workload—it worked. I'm reaching new audiences that I've never reached before.
8) Industry hypocrisy is nuts. The same creators publicly calling AI-assisted content "slop" are privately DMing me asking how to do it themselves (you know who you are 😂).
Top creators are already leveraging the tools and multiplying output and quality -- whether through an avatar or thumbnails, scripting, and editing.
And the content explosion is just getting started.
My best advice to take advantage of this opportunity would be to start experimenting every day with AI and finding workflows that work for you.
I'd start here:
- Claude 3.7 Sonnet for editing and polishing scriptwriting and title generation (paste your scripts + prompt "make it better" or "make it more viral")
-GPT4o for thumbnails and image b-roll
-KLING for video b-roll
-Heygen or Synthesia for AI avatar cloning
-ElevenLabs for voice cloning
-Descript (if you're new to editing)
In the end, I think if you’re not using all the available tools to create better and more content as a creator, you're doing your audience a massive disservice.
It's time to start embracing the tools and serving your audience better!
First, they scammed you on skin cancer when the sun is good for you.
Now, they're scamming you again on cholesterol to sell you a lifetime medication.
This entire narrative of cholesterol being the villain in heart disease was built on a lie.
What doctors fail to tell you is that the sugar industry bribed scientists to shift the blame of heart disease from sugar to cholesterol. This has been revealed by internal documents that have surfaced.
The result? A massive push for statins, now taken by 35% of Americans over 40, with devastating consequences.
Studies now show that after five years of daily use, the average person gains only three to four extra days of life—just a few days for a lifetime of potential harm.
Even more alarming, 20% of statin users suffer serious injuries like muscle deterioration, liver damage, and nerve dysfunction. For nearly half of all patients, the side effects are so unbearable that they quit within a year.
The evidence is clear: statins are not the life-saving drugs we’ve been told they are.
If you don't believe me, watch Jimmy Dore break down this article by @MidwesternDoc and be prepared to have your mind blown.
Everyone talks about legendary writers like:
Hemingway, Stephen King, or Henry David Thoreau.
But there is a British author who redefined the game forever.
Here’s the secret technique J. K. Rowling used to write one of the best-selling book series of all time:
Two thoughts from Stephen McCranie
“The master has failed more times than the beginner has even tried.”
“When you procrastinate you become a slave to yesterday.”
I have been using ASCII Art as a way to bypass all of the ridiculous “alignment” for “safety” on AI for over 2 years.
Now it is a subject of a university paper.
This is just one of 37,831 techniques I can use to overcome their Orwellian world.
Here is how it works: