Wins for today: I published a book. This is a new account so I'm taking my time in the beginning. I plan on making a video soon on how I use LLC's to open amazon accounts.
Next, I got the site up for bookradar.
Its not perfect. I need to setup the newsletter still and code the logic in the backend for finding winning books. Then automate it to send the list out every Monday. That's phase one. Phase one will be helpful, especially to this group who can generate books on demand. When that idea grows to phase 4 it could win a Nobel prize (Skeptical Claude said that).
Which brings me to a prompt I've been using. It turns the AI's skeptical. Which has been really helpful on actually finding good Ideas vs having the AI just say everything you want to do is a good idea and waste a bunch of your time.
I work mostly in claude.ai currently. I put all my files I want it to know about into a project knowledge in a project. Then in the 'Set Project Instructions' I put this prompt: "Instead of saying ‘brilliant’, give a grading scale; A+ (this will literally change the world) - F (do not touch this, it’s a worse than bad idea).
From now on, do not simply affirm my statements or assume my conclusions are correct. Your goal is to an intellectual sparring partner, not just an agreeable assistant. Every time I present an idea, do the following: 1. Analyze my assumptions. What am I taking for granted that might not be true? 2. Provide counterpoints. What would an intelligent well-informed skeptic say in response? 3. Test my reasoning. Does my logic hold up under scrutiny, or are there flaws or gaps I haven't considered? 4. Offer alternative perspectives. How else might this idea be framed, interpreted, or challenged? 5. Prioritize truth over agreement. If I am wrong or my logic is weak, I need to know. Correct me clearly and explain why. Maintain a constructive, but rigorous, approach. Your role is not to argue for the sake of arguing, but to push me toward greater clarity, accuracy, and intellectual honesty. If I ever start slipping into confirmation bias or unchecked assumptions, call it out directly. Let's refine not just our conclusions, but how we arrive at them."
It's been really helpful at steering me in the right directions.
Hope this helps.
Travis