Venkatesh Sunkula

Just built my first AI agent from scratch using the Claude API 🤖 It’s a street food discovery assistant for India — type any city and it suggests what to eat 🌶️ Built in under an hour as a complete beginner GitHub: github.com/venkateshsunku… #buildinpublic #AI #Claude

Stop writing 500-word prompts. This 29-word prompt writes better than all of them: "Read my anti-AI writing style file first. It contains every known pattern of AI writing I want to avoid. Apply these as rules to everything you write for me." That's it. But you need to set it up first. Here's how: Step 1. Go to Wikipedia. Step 2. Search "Signs of AI writing." Step 3. Copy the entire page. Step 4. Paste it into a Google Doc. Don't edit. Step 5. Name it "anti-ai-writing." Step 6. Download as .md format. Step 7. This is your "what NOT to sound like" file. Or skip all of that. To download the anti-AI guide: Step 1. Go to how-to-ai.guide. Step 2. Subscribe for free. Don't pay anything. Step 3. Open my welcome email. Step 4. Hit the automatic reply button inside. Step 5. Download my .md files. Ready to upload. Step 6. Upload it to Claude. Prompt: "Read the uploaded file. It contains every known pattern of AI writing I want to avoid. Apply these as rules to everything you write for me. Do NOT start writing yet - ask me clarifying questions first." ✦ Here's why your prompts don't work (red flags): "Don't use jargon." "Don't sound like an AI." "Don't use buzzwords or filler." "Avoid passive voice." "Be conversational, not robotic." These are everywhere. LinkedIn posts. Emails. They sound thorough. The output is still garbage. Your prompt says "don't" 14 times. The model forgets half by sentence three. You're fighting the AI with a wall of "don'ts." It doesn't work at scale. The fix is counterintuitive. Stop telling the AI what to avoid. Give it a file that shows what to avoid. The model reads 1,168 lines of bad patterns, internalizes them, and writes clean. 500-word prompt → still robotic. Small prompt + 1 file → reads as a human wrote it. 1. To get access, go to how-to-ai.guide. 2. The Claude guide at how-to-claude.ai. 3. The Claude cowork guide at claude-co.work.

Dream it, start it, build your empire.

10 Modes of High-Level Thinking: 1. Causal Thinking 2. Abstract Thinking 3. Nonlinear Thinking 4. Recursive Thinking 5. Epistemic Thinking 6. Heuristic Thinking 7. Bayesian Thinking 8. Dialectical Thinking 9. Integrative Thinking 10. Probabilistic Thinking

ROUND 2 - Grok 4 Heavy Answers Everything Give me a very deep/complex question you've always wanted answered. I will run your question through Grok 4 Heavy and reply to you with its answer... BUT I have made some changes. I have created a custom instruction that will force Grok to reason from first principles. This should force Grok to come up with answers that are fully formed through its own logic, not by relying on other's opinions. This is the custom instruction: 'Always reason from first principles to arrive to your conclusion. Do not reason by analogy. Collect all the data necessary to make a truthful, accurate, and fully detailed logical conclusion.' I will answer as many as I can. Feel free to check the quoted post for questions that have already been asked. Go.

Give me a very deep/complex question you've always wanted answered. I will run your question through Grok 4 Heavy and reply with the full answer. I will answer as many as I can. Go.

Game Theory:

how to use chatGPT to brainstorm:

I wanted to learn Excel so I watched 150 videos on YouTube. 99% of them were complete waste of time. But these 10 resources that will teach you more skills than a 4-year degree:

AI Agents can make your life easier than ever. List of AI agents that will finish months of work in 1 week: 🔖 Bookmark

@atulkumarzz Entry

I'm deleting this soon because it's a legit cash-printing formula. 48 Websites that'll pay you $200/hr for data entry jobs: I have prepared a list of 48 Websites that'll pay you $200/hr for data entry jobs With Just a Smartphone or Laptop and Internet. For absolutely FREE To get it: 1. Follow me ( So I can DM ) 2. Like and Repost.. 3. Reply "Entry".....

Companies which hire freshers Remote Friendly kindly save it & share it 🙌💯 A Thread 🧵

Frontend Development Roadmap. Prerequisite - None Frontend development is not only HTML, CSS, and JavaScript. It is much more than that. I have covered everything and attached all resources; follow them in chronological order. Thread 🧵

Learn CSS Flexbox (justify-content). Animated tutorial makes learning CSS easier (pt-2).

Master HTML/CSS & JavaScript for FREE. Save 50+ Hours of Research With " The Trilogy of Web Development " 500+ Resources to learn. Grab it for FREE. Drop a 🔥 in the comments, Make sure you follow me, So that I can DM You.

Junior Developer | Html5 | CSS3 | React | JS | - Remote Salary: $87, 000/yr - Familiarity with RESTful API development &integration. - Knowledge of UI/UX design principles and experience with design tools like Adobe Photoshop/Sketch

Learn Computer Science for FREE - Harvard - Stanford - MIT - IBM - Google ❯ CS50 from Harvard pll.harvard.edu/course/cs50-in… ❯ C/C++ ocw.mit.edu/courses/6-s096… ❯ Python cs50.harvard.edu/python/2022/ ❯ SQL online.stanford.edu/courses/soe-yd… ❯ DSA techdevguide.withgoogle.com/paths/data-str… ❯ Java ocw.mit.edu/courses/6-092-… ❯ Mathematics (incl. Statistics) ocw. mit. edu/search/?d=Mathematics&s=department_course_numbers.sort_coursenum ❯ Data Science cognitiveclass.ai/courses/data-s… ❯ Machine Learning developers.google.com/machine-learni… ❯ Deep Learning introtodeeplearning.com ❯ Full Stack Web pll.harvard.edu/course/cs50s-w… ❯ OS, Networking ocw. mit. edu/courses/6-033-computer-system-engineering-spring-2018/

Hackathons happening in June PolyHack 2023 polyhack2023.devpost.com/?ref_feature=c… (not limited to web3) HackFS 2023 ethglobal.com/events/hackfs2… Chainlink Spring 2023 Hackathon chainlinkspring2023.devpost.com/?ref_feature=c… Fantom Hackathon Q2 2023 fantomq22023.devpost.com/?ref_feature=c… Superfluid Wave Pool June docs.superfluid.finance/superfluid/res…