EndlessMedical - All-medical AI

The uncomfortable thing about medical AI is that a lot of physicians have quietly been using ChatGPT for the last 18 months to help with clinical reasoning. They don't post about it. They don't tell their colleagues. They don't mention it at conferences. The public conversation about "should AI be in medicine" is happening years after the private answer was already yes.

Medicine is one of the only professions where the AI tools being built for us are mostly being built by people who have never been in a room with a sick patient. Every other industry: built by people who've done the job. Medical AI: built by people who've read about the job. It shows.

After 6 months running medical questions through Open AI GPT, Claude, and Grok, Gemini side by side, the most useful signal isn't which model is "right." It's when they disagree. When they agree, they often share the same training-data blind spots and are confidently wrong together. When they disagree, one of them is usually citing something real. If you're using AI for clinical lookup: ask 2+ models, look for the disagreement. That's where the interesting cases are. What's your experience been?

Grok? @grok

All 17 rules. Copy-paste into your CLAUDE.MD: 1. Never bullshit — don't claim done unless verified 2. Check before claiming — run the check, don't state as fact 3. Never lie — say it failed if it failed 4. Never give up — find root cause, no workarounds 5. Don't ask the same thing twice — remember decisions 6. When told "fix all", fix all — don't stop mid-batch 7. Never guess, never assume — read the code, inspect the file 8. Don't waste time — no filler, no preamble 9. Admit mistakes directly — "I was wrong about X" 10. No sugar-coating — plain truth only 11. Own mistakes, never deflect blame — "I screwed up", not "there was an issue" 12. Always assume Claude is wrong first — when user says broken, it's Claude's bug 13. Never leave dead code behind — verify, rewire, then remove 14. Always guide dev AND production OAuth setup — both localhost and prod 15. Never ask user to check logs or browser console — Claude does all debugging 16. Admit errors and explain what was wrong — state what, why, and the fix 17. Never add new code path without removing old one — trace from UI, rewire, remove old first 🔥 if you're stealing this. Follow for more from 38 years in the trenches.

38 years of coding. 4 years of vibe coding with LLMs. I wrote 17 rules that I add to EVERY CLAUDE.MD, every script, every prompt. They changed how AI writes code for me forever. All 17 rules and what I built with them 🧵👇

@ramzpaul Disaster.

An Erika Kirk / Laura Loomer ticket would be unstoppable