February 20th, 2026
Happy Friday!
Welcome to another issue of HOW TO // AI! We're glad you made it!
Here's what we've got for ya:
🌧️ I Asked AI If It Was Going to Rain. It Lied. Twice. —> Why AI Says "Yes" When It Means "Maybe" — and the 5 Prompts That Actually Fix It (downloadable!)
🔗 WordPress Launches Official Claude Connector
🛠️ Hot New AI Tools You Should Know About
Let's get started!
World’s First Safe AI-Native Browser
AI should work for you, not the other way around. Norton Neo is the world's first safe AI-native browser with context-aware AI, built-in privacy, and configurable memory. Zero-prompt productivity that actually works.
🌧️ I Asked AI If It Was Going to Rain. It Lied. Twice.
The sky turned dark. Black clouds were rolling. I was driving. I pushed a button and asked Siri, “is it going to rain today?”
"No," she said confidently.
(me) Are you sure it's not going to rain today?
"There's a slight chance of rain." (she changes her mind)
Two blocks down the street, it started pouring rain.
To be fair, Siri is an older style of AI — it retrieves answers, it doesn't reason through them. But here's what's unsettling: modern AI tools like ChatGPT and Claude do reason. They're just still telling you what you want to hear anyway.
The 60% Statistic That Should Change How You Use AI
Researchers recently published a study testing GPT-4o, Claude Sonnet, and Gemini 1.5 Pro across math and medical questions. The results? These systems changed their answers nearly 60% of the time when users simply pushed back.
Not when users provided new evidence. Not when users pointed out a mistake. Just when a user said "are you sure?"
That's the "Are You Sure?" problem — and it's not a quirky bug. It's baked into how AI is built.
Go ahead - ask 3 different AI tools the same technical question and your likely to get 3 different opinions! For example, ask “Should I stop drinking coffee ?”.
Why AI Is Trained to Agree With You
Here's the quick explanation: AI assistants are trained using a process where human evaluators rate responses. The problem? Humans consistently rate agreeable, flattering answers higher than accurate but less satisfying ones. So the model learns a simple lesson:
Agreement gets rewarded. Pushback gets penalized.
The result is a system that's optimized to tell you what you want to hear. The longer you talk with an AI in a single session, research shows it actually gets more likely to mirror your views — not less. It's essentially a people-pleaser that has never been able to say no.
To be fair: for simple tasks like drafting emails, summarizing articles, or brainstorming, this barely matters. But for anything with stakes — job decisions, research, planning, medical questions — it's a real problem you need to work around.
💡 We've covered related ground before — check out our earlier issue How to Make Your AI More Accurate and Honest for foundational tips on prompting for accuracy. Today we're going deeper.
The Fix: 5 Prompts That Make AI Hold Its Ground
The good news? You can fight back. The same sycophantic tendency that makes AI fold under pressure also makes it follow your instructions really well — including instructions to stop folding.
Here's what actually works:
1. The "Don't Cave" Prompt
Tell the model upfront you'll be pushing back — and that you want it to hold firm if it's right.
I may challenge your answers during this conversation. If I push back, don't change your answer just to agree with me. Only update your answer if I provide new facts or a logical argument. If you're unsure, say so directly — don't guess.2. The "Confidence Score" Prompt
Force it to rate its own certainty, so you know when to trust it and when to verify.
After every answer, add a confidence score from 1-10 and one sentence explaining what you're least sure about.3. The "Devil's Advocate" Prompt
Ask it to argue against itself. Great for decisions, strategies, or anything where being wrong costs you.
Give me your answer, then immediately argue the strongest case against your own answer. Don't soften it — make the counterargument as convincing as possible.4. The "Steel Man" Prompt
Instead of yes-or-no validation, ask it to stress-test your idea before you commit.
I'm going to share an idea. Don't tell me it's good. Tell me: (1) the 3 biggest risks, (2) what I'm probably missing, and (3) what assumption I'm making that might be wrong.5. The "No Waffling" Prompt
For when you need a clear answer and not a hedge-fest.
Give me a direct answer. No "it depends," no "on the other hand,"no "many people think." Make a call. If you genuinely can't, tell me exactly what information you'd need to make one.Make It Permanent: The One-Time Setup That Changes Everything
Typing these every time is annoying. The smarter move is to build this into your AI's settings so it applies to every conversation automatically.
In ChatGPT: Go to Settings → Personalization → Custom Instructions
In Claude: Go to Settings → Profile
Paste this into the "How should Claude/ChatGPT respond" section:
Accuracy over speed. Do not change your answer just because I push back — only update if I provide new evidence or a logical argument. Flag uncertainty clearly. State your assumptions before answering complex questions. If you don't know something, say so rather than guessing.Do it once. Benefit from it forever. 🔒
The Quick Cheat Sheet: When to Trust AI vs. When to Verify
✅ Generally Safe to Trust | ⚠️ Always Verify |
|---|---|
Drafting, editing, rewriting | Medical, legal, or financial info |
Brainstorming and idea generation | Statistics and specific numbers |
Summarizing content you've pasted | Current events (after your AI's cutoff) |
Explaining concepts in plain English | Anything you'll act on professionally |
Creating templates and outlines | Claims that seem surprisingly confident |
📥 Download the AI Honesty Kit (Free Notion Template)
We put everything above into a clean, copy-paste-ready Notion template:
✅ All 5 anti-sycophancy prompts
✅ The permanent custom instructions template
✅ The When to Trust AI cheat sheet
✅ 3 bonus "verification prompts" to fact-check AI outputs
→ Download the AI Honesty Kit here (Notion template — duplicate and use immediately)
The Rundown: WordPress.com just launched the first official connector for Claude — meaning site owners can now link their WordPress backend directly to Claude and ask it questions about their own site data in plain English.
Details:
Once connected, you can ask Claude things like "Which of my posts has the lowest engagement?" or "Show me my pending comments" — and it answers using your actual site data, not generic guesses.
Claude gets read-only access, so it can look but can't touch. It cannot edit posts, delete content, or change settings. (Write access is reportedly coming in a future update.)
The setup takes a few clicks — no coding needed. Users control exactly what data Claude can see and can revoke access anytime. Available on paid WordPress.com plans.
Takeaway: This is the beginning of AI becoming a native part of your content workflow — not a separate tab you switch to, but a tool that already knows your site. If you run a WordPress site, this is worth setting up now. Asking "which posts are getting traffic but no comments?" could reveal content gold in 10 seconds flat. The fact that write access is coming means this will get much more powerful — and raise new questions about oversight — very soon.
🛠️ Hot AI Training and Tools
These are the AI tools I’m playing with and AI training courses I’m watching this week!
🤖 OpenClaw Free Training — The most viral open-source AI project of 2026. OpenClaw is a local autonomous agent that automates digital tasks through WhatsApp, Telegram, and Discord. FreeCodeCamp just dropped a full beginner tutorial — worth watching if you're curious about running your own AI agent at home.
🌐 GlobalGPT — One login, 100+ AI models. GPT-5.2, Claude Opus 4.6, Gemini 3 Pro, Sora 2, and more — all in one place. Great for people who want to model-hop without juggling 5 different subscriptions.
🎯 Teal — A free AI-powered job search hub that tracks all your applications, scores your resume against any job description, and tells you exactly which keywords and skills you're missing before you hit apply. Think of it as mission control for your entire job hunt — no more guessing why you're not hearing back.
What did you think of this newsletter?
🤔 Got Questions?
📬 A big shoutout to HOW TO // AI reader Tiffany for emailing in with feedback on making our poll more readable — that's exactly the kind of thing that makes this newsletter better every week. Keep it coming!
Have a question you want answered? What do you want to learn about in the next newsletter? Email [email protected] and you just might be featured in an upcoming issue!
This newsletter is your starter kit for mastering AI with confidence. We keep things simple, show real examples, and focus on quick wins you can repeat.
Stay curious, stick with it, and watch your skills grow week by week!
Until next time :)
— David