Here's my 5-hour conversation with Dylan Patel and Nathan Lambert on DeepSeek, China, OpenAI, NVIDIA, xAI, Google, Anthropic, Meta, Microsoft, TSMC, Stargate, megacluster buildouts, RL, reasoning, and a lot of other topics at the cutting edge of AI. This is was a mind-blowing,

Day 🔟/100: Recap Day!! It has been 10 days since we started learning about Prompt Engineering. Let's do a short recap today before we learn more. We started by learning about the following prompt pattern: 1. Contextual pattern 2. Template pattern 3. Outline expansion pattern

OmniHuman-1 by ByteDance is very good. Video from one photo!!?? This is the new world. #OmniHuman #ByteDance #AI

Doesn’t get better than this!! I ll try out an idea on my train ride. What about you? #Replit #AI

Day 1⃣1⃣/100 Let's look at different prompting techniques today. We will start with basics. Today we will look at zero-shot vs one-shot prompting. 🎯 Zero-shot vs. One-shot prompting in AI 🔹 Zero-shot: No examples provided — best for simple, well-defined tasks. Example:

This account is 🔥 .. The goal is to give the average person the insights of an institutional investor for free. Use X to quickly test what people want, engage with them for feedback, and roll it onto the main Perplexity app. Invest Like The Best!

A firestorm of debate has ignited in India since I walked off a podcast due to the poor air quality. Indians, organize yourselves and take action. You will do more to improve India’s health by cleaning up the air than by curing cancer.

THIS but also don’t keep doing the same thing that doesn’t work Ask questions, adjust, iterate, and most people would do well to do it at a higher velocity

Day 1⃣2⃣/100 : Chain-of-Thought prompting technique Let's learn about chain-of-thought prompting technique. What is it? Why is it important? As the name suggests, chain-of-thought prompting invokes the thought process involved in solving or answering a prompt. The prompt

Anduril is taking over IVAS, and we don't have time for business as usual. Whatever you are imagining, however crazy you imagine I am, multiply it by ten and then do it again.  I am back, and I am only getting started.

Day 1⃣3⃣/100: Let's look at reasoning models in LLMs. 1. #DeepSeekR1: Its reasoning mode is amazing, handling logical and math problems well. DeepSeek excels at showing deliberations and then choosing/calculating the correct answer. 2. #OpenAI O3-Mini: Reasoning can be accessed

Watchlist, tracking your portfolio, analyzing imaginary portfolios, comparing them, getting news about stocks you own: all are in our plans. We are going to do it for sure. Just needs some time. A dirt cheap widely accessible Bloomberg Terminal for all is the dream.

“Do not make any small plans, because it cannot inspire the soul” - John D. Rockefeller

The last 24 hours has had SO much tech news. — Microsoft Majorana 1 quantum chip — Google AI co-scientist — xAI Grok 3 model release — Clone musculoskeleton — Claude reasoning coming soon — Arc institute biological model — Sakana AI CUDA kernel optimizer All the threads here:

Day 1⃣4⃣/100 What is Prompt Chaining? Prompt chaining is a technique where multiple prompts are used in sequence, with each step refining or expanding the previous output. This improves accuracy, coherence, and reasoning in AI-generated content. How does Prompt Chaining work?

AI Agents are the future!

Big news! On March 3rd, our book Prompt Engineering in Action is the Deal of the Day at 45% off! shivendra Manning Publications Don't miss this one-day-only deal! Grab your copy here: mng.bz/WrEx #AI #PromptEngineering #GenerativeAI #MachineLearning