Jac-Martin Dorion (@miraclemart) header
Jac-Martin Dorion (@miraclemart) profile picture

Chief Creative Officer, AI prompt criticologist, keyboard enthusiast

Atlanta
Joined August 2008
Photo by Jac-Martin Dorion (@miraclemart)Photo by Jac-Martin Dorion (@miraclemart)Photo by Jac-Martin Dorion (@miraclemart)Photo by Jac-Martin Dorion (@miraclemart)Photo by Jac-Martin Dorion (@miraclemart)Photo by Jac-Martin Dorion (@miraclemart)Photo by Jac-Martin Dorion (@miraclemart)Photo by Jac-Martin Dorion (@miraclemart)Photo by Jac-Martin Dorion (@miraclemart)Photo by Jac-Martin Dorion (@miraclemart)
Jac-Martin Dorion retweeted
Config 2027 is coming to Pier 80 in San Francisco May 25-27 Want to be a speaker? Time to apply.
26
40
9
637
3,601,632
Jac-Martin Dorion retweeted
I absolutely hate AI writing. And my entire job is to write about AI. So I keep a file of the new em-dash to recognize AI writing instantly: Everyone learned the em dash trick. AI is trained to not write with em dashes anymore. Now you can get accused of using AI if you write in perfectly structured sentences. These are some of the dead giveaways of using AI: 1. "That's not X. That's Y." "That's not compliance. That's stalling." Say the second half only. "They're stalling." 2. Two short bits stuck together. "Fast. Simple." "No fluff. Just answers." Pick only one to write like a real person. 3. "Less a hammer, more a scalpel." Visualizing two pictures with no advice. Directly say what to do instead. 4. Clapping for itself. "And that matters." "That's the part everyone misses." "Which is exactly the point." Delete them all. You lose nothing. I promise. 5. "It's the Excel of AI agents." Only works if I know both things. Usually I don't. 6. Warming up before talking. "Here's the thing." "Let me be clear." "The truth is." Start one sentence later. 7. Always three things. "Faster, cheaper, smarter." Real life gives you two reasons. Or five. Never always three. 8. "5 to 10 minutes." A range means you never did it. Just say 7 minutes. 9. The ending that repeats the whole post. "In short…" "At the end of the day…" Just stop typing. End on a high note. Now that you know how AI writes. Here's how to actually stop AI from doing all nine: Step 1. Type only these two words in your prompt. Open chat & write: "Use ASD-STE100." That's the writing standard for plane manuals. Short words, short sentences, because a confusing sentence there can kill someone. Claude already knows it. Those words remove 80% of the bad writing. Works on ChatGPT, Gemini & Grok too. Step 2. Get the skill so you never type it again. I built the full version with every rule inside. It's free: ste.rubenhassid.ai Download the zip. In Claude, click Customize on the left. Click Skills. Click Upload a skill. Drop the zip in. Type /ste to use it. Step 3. Turn it off for fun stuff. I asked it for a poem. Unreadable. I asked it for a LinkedIn post. It sounded German. Use /ste for guides, steps, explanations, emails, documents. Turn it off for anything with a heart. Step 4. Add 4 lines to your claude .md. "follow Zinsser's four principles of quality writing: 1. Simplicity 2. Brevity 3. Clarity 4. Humanity" /ste gives you the first three but forgets about the fourth. This prompt puts it back on the track. Step 5. Make a forbidden .md. Copy the 9 patterns above into a file. Tell Claude to check every draft against it. Then add a new line every time you spot one. Your file gets better every week. Mine certainly does. Step 6. Start a new chat more often. If your chat is long, the writing gets worse. It repeats itself & goes back to the pretty sentences. When it feels half full, open a fresh chat & paste your files back. The skill is free, right in your inbox: ste.rubenhassid.ai
265
461
65
6,226
1,025,022
The Prompt Box states I reached my Usage limit, while the Usage Settings screen says everything is frosty. Did anyone encounter this on Pro Plan? #claudelimits #claude
62
Jac-Martin Dorion retweeted
Anthropic dropped a 33 page cheat sheet for using Claude to build and design anything. resources.anthropic.com/hubf…
31
311
14
3,513
687,068
Jac-Martin Dorion retweeted
We’ll meet you in Arena Breakout, chooms. 🔺10.16.2025🔻
🚨 Arena Breakout x @CyberpunkGame 2077 is live on OCTOBER 16! Collab skins and exclusive events will be available in Kamona. Cyberpunk meets realistic military FPS—intense battles under the neon lights. Are you ready to dive in? Stay sharp! More intel incoming. 😎 #Cyberpunk2077 #ArenaBreakoutS10 #LivingLegend
27
102
1
2,174
195,964
Help me bring back the Drop BMR1 Nearfield Monitors to @drop! Request it here: dro.ps/b/NxNhmOVK7kQO/t?mode…
1
359
Jac-Martin Dorion retweeted
They won’t fear it until they understand it. And they won’t understand it until they’ve used it. Watch the trailer for #Oppenheimer. In theaters 7 21 23.
2,027
20,381
7,981
95,475
104,335,293
Jac-Martin Dorion retweeted
Every Monday lately
94
1,074
68
11,122
Stayed for the day, and missed the con! Wish I’d stay another day! #Bitcoin #Bitcoin2022
Jac-Martin Dorion retweeted
We recommend not looking
84
1,571
74
10,273
This is the best part! Going for dark humorous aesthetics. #mk #mt3 #mito get yours here… dro.ps/mt3cyber-tw
Jac-Martin Dorion retweeted
[GB] GMK ZEN POND live now The new CJ is out today!😻
2
3
2
30
Looking good! Love the low profile look.
[IC] ePBT WINTER BREATH -Group Buy Coming Soon -The theme is winter camp and pine forest. Interest check opened at KBDfans!
Jac-Martin Dorion retweeted
Patch 1.23 is available on all platforms! The list of changes for this update is available here: cp2077.ly/Patch1_23
993
1,206
348
13,150
Jac-Martin Dorion retweeted
Here’s all ten episode titles of Rick and Morty Season Five, premiering June 20th only on @adultswim
156
1,975
434
11,907
Jac-Martin Dorion retweeted
ICYMI Rick and Morty Season 5 premieres Sun, June 20 on @AdultSwim.
171
2,787
574
16,971
Dear @CDPROJEKTRED No need for apologies! #CP2077 looks amazing! I love the gameplay on #XboxOneS, highly engaging. Bugs are expected, games still have bugs years after launch. en.cdprojektred.com/?p=82838