Post

How to get URL link on X (Twitter) App

On the Twitter thread, click on or icon on the bottom
Click again on or Share Via icon
Click on Copy Link to Tweet
Paste it above and click "Unroll Thread"!
More info at Twitter Help

Hasan Toor

@hasantoxr

Mar 27, 2023 • 13 tweets • 7 min read • Read on X

Scrolly

Harvard University offers a ton of FREE online courses.

From Computer Science to Artificial Intelligence.

Here are 10 FREE courses you don't want to miss:

1. Introduction to Computer Science

An introduction to the intellectual enterprises of computer science and the art of programming.

Check here 👇

pll.harvard.edu/course/cs50-in…

2. Web Programming with Python and JavaScript

This course takes you deeply into the design and implementation of web apps with Python, JavaScript, and SQL using frameworks like Django, React, and Bootstrap.

Check here 👇

pll.harvard.edu/course/cs50s-w…

3. Introduction to Programming with Scratch

A gentle introduction to programming that prepares you for subsequent courses in coding.

Check here 👇

pll.harvard.edu/course/cs50s-i…

4. Introduction to Programming with Python

An introduction to programming using Python, a popular language for general-purpose programming, data science, web programming, and more.

Check here 👇

edx.org/course/cs50s-i…

5. Understanding Technology

This is CS50’s introduction to technology for students who don’t (yet!) consider themselves computer persons.

Check here 👇

pll.harvard.edu/course/cs50s-u…

6. Introduction to Artificial Intelligence with Python

Learn to use machine learning in Python in this introductory course on artificial intelligence.

Check here 👇

pll.harvard.edu/course/cs50s-i…

7. Introduction to Game Development

Learn about the development of 2D and 3D interactive games in this hands-on course, as you explore the design of games such as Super Mario Bros., Pokémon, Angry Birds, and more.

Check here 👇

pll.harvard.edu/course/cs50s-i…

8. CS50's Computer Science for Business Professionals

This is CS50’s introduction to computer science for business professionals.

Check here 👇

pll.harvard.edu/course/cs50s-c…

9. Mobile App Development with React Native

Learn about mobile app development with React Native, a popular framework maintained by Facebook that enables cross-platform native apps using JavaScript without Java or Swift.

Check here 👇

pll.harvard.edu/course/cs50s-m…

10. Introduction to Data Science with Python

Join Harvard University instructor Pavlos Protopapas in this online course to learn how to use Python to harness and analyze data.

Check here 👇

pll.harvard.edu/course/introdu…

Bonus:

If you are interested in learning about ChatGPT & GPT-4

Then I built this Ultimate GPT-4 Guide:

• 50+ Chapters
• 700+ No Code & AI Tools
• 1000+ GPT-4 Prompts

Here is the free link for everyone:

hasantoxr.gumroad.com/l/gpt4

@hasantoxr

That's a wrap!

If you enjoyed this thread:

1. Follow me @hasantoxr for more of these
2. If you enjoyed this thread, don't forget to like, comment, and retweet the first tweet.

https://twitter.com/1506055005992026115/status/1640255142480998400

• • •

Missing some Tweet in this thread? You can try to force a refresh

This Thread may be Removed Anytime!

Twitter may remove this content at anytime! Save it as PDF for later use!

More from @hasantoxr

Hasan Toor

@hasantoxr

Feb 10

🚨BREAKING: Someone just built an AI mechanic for broken vibe-coded apps.

It's called FixMyApp AI and it fixes your broken AI-built MVPs without prompting, agencies, or rewriting anything.

Just connect your repo → describe the bug → get a PR in 48 hours.

Here's how:↓

Here's the problem nobody talks about:

Cursor, Bolt, Replit, Lovable they're incredible at building MVPs.

But the moment you push to production?

Auth breaks. APIs timeout. Edge cases everywhere.

You're stuck prompting in circles trying to fix code you didn't write.

Why this hits different:

Most founders vibe-coding their MVP aren't engineers.

They can BUILD with AI but can't DEBUG with AI.

FixMyApp isn't another AI wrapper.

It's actual human engineers who understand AI-generated codebases because that's ALL they work on.

Read 6 tweets

Hasan Toor

@hasantoxr

Feb 6

Everyones using ChatGPT for content writing. Meanwhile Claude is quietly outperforming it on every platform.

I switched 3 months ago and my engagement jumped 340% across all socials.

The secret isnt Claude itself. Its the 10 prompts that make it write like an actual human, not a corporate robot.

Here they are: 🧵

1. The Coffee Shop Test

Prompt:

"Write this like you're explaining it to a friend over coffee. No marketing speak. No corporate jargon. Just straight talk about [topic]. If it sounds like a LinkedIn post, rewrite it."

Claude actually gets this. ChatGPT still sounds like it's pitching a SaaS product.

2. Voice Finder

Prompt:

"Give me 5 different ways to say this same idea. Make each one sound like a different person wrote it - one cynical, one excited, one skeptical, one matter-of-fact, one surprised."

This is how I find MY voice. Pick the version that feels most natural, then Claude refines it.

Read 13 tweets

Hasan Toor

@hasantoxr

Feb 6

Holy shit... Someone just built an AI CFO that catches financial problems BEFORE they destroy your startup.

It's called Nume and it monitors your finances 24/7 without dashboards or prompting.

No finance degree. No spreadsheets. No "wait, where did the money go?"

Here's how it works: ↓

Most finance tools show you dashboards you'll never check.

@NumeAI does the opposite: it watches your money 24/7 and TELLS YOU when something's wrong.

Like a real CFO sending you a Slack message: "Your burn rate just spiked 34%."

No login. No navigation. Just alerts that matter.

Try it: nume.ai

I connected QuickBooks and my bank account in 6 minutes.

Within 10 minutes, Nume found 3 cash flow problems I didn't know existed.

No tutorial. No onboarding call. No "wait, which dashboard do I check?"

It just started telling me what was wrong and why it mattered.

Read 9 tweets

Hasan Toor

@hasantoxr

Feb 4

This site is literally a prompt library with 1000+ engineered prompts.

100% free.

Check it out: promptly.fyi/library

BONUS:

I also post content on Instagram.

So, if you want to get insights with my videos, then do follow me here:

instagram.com/hasantoxr

Read 4 tweets

Hasan Toor

@hasantoxr

Feb 1

After 2 years of using AI for research, I can say these tools have revolutionized my workflow.

So here are 15 prompts across Claude, Gemini, ChatGPT, and Perplexity that transformed my research (and could do the same for you):

1/ LITERATURE REVIEW → Claude Sonnet 4.5

"Analyze these 30 papers on [TOPIC]. Find contradictions, research gaps, and emerging debates. Prioritize findings that challenge consensus."

Why Claude: 200K context window = reads entire papers, not just abstracts.

2/ RESEARCH QUESTION REFINEMENT → ChatGPT 4o

"My broad interest: [TOPIC]. Generate 10 falsifiable research questions. For each: explain methodology, expected contribution, and why current literature can't answer it."

Why 4o: Extended reasoning catches scope creep and logical gaps.

Read 18 tweets

Hasan Toor

@hasantoxr

Jan 31

After spending $5,000 on prompt engineering courses, I realized they're all teaching outdated techniques.

Here are 6 powerful prompts that actually matter in 2026 (copy & paste into Grok, Claude, or ChatGPT):

1. Deep researcher

Prompt:

"I'm researching [topic]. First, break down this topic into 5 key questions that experts would ask. Then for each question: 1) Provide the mainstream view with specific examples, 2) Identify 2-3 contrarian perspectives that challenge this view, 3) Explain what data or evidence would prove each side right. Finally, synthesize this into a framework I can use to evaluate new information on this topic."

Researchers waste weeks reading scattered sources.

This structures your entire research process upfront. I used this to write a market analysis that landed a $50k client.

2. The content mutation engine

Prompt:

"Here's my core idea: [paste idea]. Transform this into 10 different formats: 1) A contrarian Twitter thread that challenges conventional wisdom, 2) A case study showing how someone failed by ignoring this, 3) A data-driven LinkedIn post with specific numbers, 4) A 'day in the life' story format, 5) A debate between two experts who disagree, 6) A historical parallel from a different industry, 7) A prediction about what happens in 12 months if people ignore this, 8) A beginner's mistake breakdown, 9) A tool/framework people can copy-paste, 10) A personal confession about when I got this wrong."

Content creators burn out creating from scratch daily.

One idea becomes 10 pieces of content. My engagement went up 290% when I stopped chasing new ideas and started mutating existing ones.