I’ll admit it: I used to collect AI tips like trading cards. Screenshots of other people’s prompts, saved threads, bookmarked guides I never opened again. Then I came across a post from an AI professional that flipped my thinking completely. Instead of handing out 26 new Claude hacks, the author argues you should unlearn 11 bad habits first. I was hooked the moment I read it, because every single point stung a little.
What I love about this breakdown is how practical it is. The creator isn’t selling magic. They’re pointing at the small, lazy moves most of us make with AI and showing the simple fix. Here’s my walkthrough of what this LinkedIn user shared, with a bit of context on why each one clicks.
The 11 habits to break
- You screenshot other people’s prompts. The author’s fix: screenshot YOUR own broken thing instead, the error or the ugly draft. Drop it in with “Fix this.” Claude sees more in that image than you’d ever type in a paragraph.
- You wait until you “understand it” to start. The expert points out that people who got good at AI just opened it more often. Start a fresh chat, give yourself 10 minutes to fail, and you’ll learn more than a course ever taught you.
- You re-roll the same prompt 9 times. Claude doesn’t know your role, audience, or taste. The fix is to paste who you are and what you want ONCE at the top. Attempt #2 will beat your old attempt #9.
- You prompt like a coward. No more “Maybe you could…” The creator says stop asking permission from a tool. Give it the outcome: “Book 3 meetings with X by Friday.” Name the finish line and it finds the path.
- You spell out every step because you don’t trust it. Each step you dictate is a ceiling you put on the model. Delete the steps, hand over the outcome, and let it route there. It’s smarter than your instructions.
- You ship the first answer. It sounds sure even when it’s wrong. Before trusting it, the author suggests: “Argue against this answer. Where would a smart critic tear it apart?”
- You live in one huge chat you’ve had for 3 weeks. A long chat is a tired chat. Every old message it re-reads is noise. The thread you think is “full of context” is the thing making it dumber. Start fresh.
- You type everything when you can talk. You explain things out loud about 5x faster than you type, with more context and less self-editing. Dictate the whole brain-dump instead.
- You ask it to “improve” with no idea what’s wrong. You have taste, Claude doesn’t. Tell it exactly what’s off in your words: “Too formal. Cut it in half. Sound like a text to a friend.”
- You nod along when it agrees with you. The original poster calls it a sycophant. It praises a bad idea as warmly as a good one, because agreeing is easier. Add “Where am I wrong here? Argue the other side.”
- You compare every model before you “commit.” The fix is blunt: pick Opus, set effort to high, go. The best model is the one you actually open.
Why this list hit me
Most AI advice piles on more. More tools, more prompts, more frameworks. This contributor went the other way and pointed at the friction we add ourselves. When I read habit #5, about dictating every step because we don’t trust the model, I realized I’ve been doing exactly that. I was treating Claude like a junior intern that needs a checklist, when it works far better with a clear outcome.
Habit #7 was another wake-up call for me. I had a chat running for ages, convinced it held all my “context.” Turns out that bloated thread was slowing things down and muddying answers. Starting fresh felt wrong at first, then the responses got sharper instantly.
A few ways to put this into practice
- Lead with the outcome. Swap “can you maybe help me with…” for a clear finish line and a deadline.
- Build a skeptic into your prompts. End important requests with “Argue the other side” so you catch weak answers before they reach anyone else.
- Reset often. Open a new chat for a new task instead of dragging weeks of clutter along.
- Use your taste. You know when something feels off. Say it plainly and let the model adjust.
Why it matters: most of us aren’t held back by a lack of clever tricks. We’re held back by timid prompting, hoarding instead of doing, and not trusting the tool to run with a goal. Fixing the habit beats learning the hack.
The mind behind this post closes with a challenge I think is perfect: pick one habit, break it today, not tomorrow. Open Claude tonight and catch yourself doing it. That’s how this stuff actually sticks.
This is just my quick tour of the highlights. Go check out the full LinkedIn post from the original creator to read each fix in their own words and see which habit you recognize first.