Where to Start with LLM and AI? Read Nate's newsletters:

Jun 09, 2025

LLM for Beginners:

These are some of my favorite posts I wrote for people starting out in AI.

Learn AI the Easy Way: a flash card set for AI models plus classroom resources

Learn AI The Easy Way: A Complete Visual Guide to All 16 of the Best AI Models In the World, Including ChatGPT, Claude, Grok, and More!

I want to make you a promise: at the end of this guide, you won’t be confused by which model is which, and which model to pick for what task. You’ll actually know…

3 months ago · 63 likes · 5 comments · Nate

Top 10 tools: My personal current top ten AI tools

Nate’s Substack

Beyond the Listicle: Ten AI Tools That Earn Their Keep After ChatGPT (that's ~0.014% of all AI tools so we exercised judgement here)

I don’t write listicles. They flatten nuance, reward shallow takes, and usually pad SEO more than they help readers. But over the past few months—on calls, in the comments, and in my inbox—I’ve heard the same quiet frustration from newcomers to AI: “I tried ChatGPT. I clicked through Copilot. Now what…

3 months ago · 66 likes · 18 comments · Nate

What I tell my Mom about AI: A letter to someone I love who isn’t in AI at all

Nate’s Substack

What I tell my Mom about AI

I wrote this in hopes that it helps you in your conversations with friends and family in your life who don’t understand AI…

3 months ago · 42 likes · 20 comments · Nate

0-5K with AI: A complete guide to getting started from scratch with AI

Nate’s Substack

From 0 to 5K: The Complete Simplified Guide to Getting Going with AI

A year ago, I sat in front of ChatGPT for two hours trying to write a high-value email where the wording really mattered. Nothing worked. Each prompt produced results worse than the last. ChatGPT could not grok my style. I finally gave up and wrote it myself in 20 minutes—and that moment of frustration taught me everything about why most of us struggle with AI…

4 months ago · 134 likes · 26 comments · Nate

The AI Productivity Stack: 27 tools in my overall AI productivity stack

Nate’s Substack

The AI Productivity Stack: 27 Tools That Actually Deliver ROI

The AI Revolution is Here - But Which Tools Actually Matter…

5 months ago · 103 likes · 4 comments · Nate

LLM Prompting:

I write these to help people master prompts, and I write a lot of them! These are my favorites, and they should apply well to current models.

How to prompt with wake words: Using variables to prompt with AI

Nate’s Substack

How to Prompt with Wake Words in ChatGPT: One Word Callouts Save Hours Prompting on Common Tasks

So this was an unexpected gift. I learned something new in prompting this week. I didn’t expect it. And I am absolutely delighted…

3 months ago · 36 likes · 22 comments · Nate

AI System prompts: What to put in those system prompt boxes

Nate’s Substack

Write Once, Save 100 Prompts: Mastering ChatGPT’s Two Secret Boxes

This post is all about one of the trickiest parts of the ChatGPT interface: Custom Instructions…

4 months ago · 40 likes · 24 comments · Nate

Anatomy of the Prompt: How to think about prompts structurally

Nate’s Substack

The Universal Anatomy of the Prompt—How and Why a Prompt Works and How to Make it Work for You

I’ve written a fair bit about prompting tricks that work well with o3 (see here and here), but o3 is by no means the only great model out there, and I think it’s helpful to get good grounding in the bones of a prompt that work regardless of the model…

4 months ago · 48 likes · 18 comments · Nate

Prompts for Automated Workflows: Build automated workflows with prompts

Nate’s Substack

Turn ChatGPT into a Sushi Conveyor Belt: 5 Prompts to Automate Workflows that (Seriously) Save Hours

I keep realizing that we are under-estimating what these models can do, and that includes me…

4 months ago · 42 likes · 23 comments · Nate

Prompting o3 and o4-mini: How to build a prompt carefully, like a good product

Nate’s Substack

Your Prompt Is the Product: Working with o3 & o4-mini-high in the Agentic Era

Great products change our view of what’s possible, and o3 has definitely done that for me in the last week or so. (Yes, it’s only been a week). This post is about taking some of the learnigns I’ve been stewing on and getting them out there for you all to learn from, dig into, and try for yourselves…

4 months ago · 58 likes · 12 comments · Nate

My prompt stack for work: My favorite 16 prompts

Nate’s Substack

My Prompt Stack for Work: 16 Prompts In My AI Toolkit That Make Work a LOT Easier

Oops I did it again (wrote an obscenely long treasury article about AI lol). I was also hungry, so the picture is a cute short stack of pancakes…

5 months ago · 116 likes · 13 comments · Nate

The Vibe Coding Bible: A complete guide to getting started with Vibe Coding

Nate’s Substack

The Vibe Coding Bible: How to Build Useful Things with Short Prompts

Introduction: What the heck is Vibe Coding…

5 months ago · 40 likes · Nate

12 Advanced Prompting Techniques: When you’ve mastered the basics, try these!

Nate’s Substack

The Prompt Spellbook: 12 Advanced Prompting Techniques for Methodical Magic

My last post on prompting was super popular, but I realized I had left some advanced prompting techniques on the table. I built this post to highlight a dozen more advanced prompting techniques that are extremely high leverage—in other words these are techniques that…

6 months ago · 45 likes · 2 comments · Nate

7 Production Grade Prompt Patterns from Claude 4’s System Prompt:

Nate’s Substack

Surfing the Guardrails: 7 Production-Grade Prompting Patterns I Stole from Claude's (Alleged) System Prompt

The alleged system prompt leak from Claude 4 teaches us something profound: Professional prompting is defensive programming, not creative writing…

Listen now

3 months ago · 50 likes · 7 comments · Nate

LLM Policy and Strategy

I write pieces pretty regularly on how to think strategically about the changes AI is pushing across the startup and policy landscapes.

NYT and ChatGPT case: The NYT forces OpenAI to break its own policies:

Nate’s Substack

The Gray Lady’s Data Dragnet: How One Court Order Just Nuked ChatGPT Privacy

I think we all need to know this, so I’m pulling it from behind the paywall and I’m sending it right now instead of waiting until Monday…

2 months ago · 54 likes · 27 comments · Nate

We killed your startup lol: A note on startup strategy in the age of AI

Nate’s Substack

We killed your startup, lol—what to build when Sam Altman keeps shipping better models

A couple of days ago I wrote about strategic frameworks guiding AI players in 2025. That post was mostly focused on how to correctly read and build against core strategic dynamics shaping AI, but it didn’t really address the elephant in the room for indie builders and startup teams…

4 months ago · 28 likes · 1 comment · Nate

2010’s Software Laws are Dead, Here’s what’s Next: How 2020’s startups are different

Nate’s Substack

Dead as a Dinosaur: 2010's Software Laws Are Gone—Here Are The Laws of the AI Age

I’ve been fortunate to witness two transformative waves in tech: first the software startup boom of the 2000s/2010s, and now the relentless surge of AI in the 2020s. Each era came with its own unwritten “laws” of success – strategic principles that every ambitious founder swore by. In this article, I’ll delve into how the guiding laws of the software era shaped legendary companies, and how today’s emerging AI giants are rewriting those rules. Along the way, I’ll draw on case studies from Facebook to OpenAI, and distill what’s changed (and what hasn’t) as we move from apps to algorithms. The goal is to develop a clear comparative framework – even a chart of new laws versus old – and give these evolving principles names. By the end, we’ll see what lessons carry forward, which playbooks belong in a museum, and how entrepreneurs and investors can navigate the brave new AI-centric world…

5 months ago · 40 likes · 10 comments · Nate

A strategy framework for AI: This guide helps you pick a strategy in the age of AI

Nate’s Substack

Why the Pipes Suddenly Matter

Look, I know most of us are not CTOs or CEOs. The last time I did a strategy Substack I noticed it kind of flopped, and I am perfectly fine with that. Don’t worry, there will be lots of articles aimed at a wider audience coming up…

4 months ago · 43 likes · 6 comments · Nate

LLM Integrations and Models:

Models age quickly these days, so I made sure these were up to date posts!

OpenAI Data Connectors: How to use OpenAI’s new Data Connectors.

Nate’s Substack

A Quick Guide to OpenAI's New Data Connectors—Here's How to Use Them in 5 Minutes Plus the Strategy Behind the Launch

What happens when you give a smart chatbot access to all your personal data…

Listen now

3 months ago · 24 likes · 7 comments · Nate

MCPs: What are MCPs and how should you think about them?

Nate’s Substack

How I Think About MCP: A Practical Guide to Tool Use in AI Agents

Here's a wild thought: what if we stopped telling AI systems exactly what to do…

4 months ago · 58 likes · 8 comments · Nate

Guide to picking a model: A handy guide to picking the right model for you

Nate’s Substack

You Will Choose Wisely: The Definitive Guide to Picking (and Paying for) an AI Plan in Q2 2025

Nate, which plan should I choose? Nate, I’m not paying $200 a month for ChatGPT Pro! Nate, is Lovable and Bolt just the same thing? Do I really need Claude too? I’ve been getting these questions a ton, and I finally just wrote a guide for it. Plus I vibe-coded a little Lovable app to help you make the right plan decision for you in 2 minutes…

4 months ago · 48 likes · 20 comments · Nate

Guide to o3 and Gemini 2.5 Pro: Specifically testing both models on common prompts

Nate’s Substack

The Complete Guide to ChatGPT o3: Includes Tests vs. Gemini 2.5 Pro, Performance at ~12 Job Skills, OpenAI Notes Review, Links to Other Reviews

So o3 dropped yesterday, April 16th. Take a breath. First, here’s the gigantic o3 model notes from OpenAI…

4 months ago · 49 likes · 9 comments · Nate

Introducing Claude 4: A deep dive on the new Claude models

Nate’s Substack

Introducing Claude 4—here's where it shines and how to use it alongside ChatGPT and Gemini

I really did feel like Christmas came early when I got early access to Claude 4 this week. I will have more on this in a few days as I start to really dig in, but my first impressions are extremely positive…

Listen now

3 months ago · 46 likes · 19 comments · Nate

LLM Futures

How should we think about our collective future in the age of AI?

Rethinking the path to AGI: What does it actually take to reach workable AGI?

Nate’s Substack

Scaling Isn’t Destiny: Rethinking the Straight-Line Path to AGI

In a little over two years, we’ve gone from being surprised that AI can write entire paragraphs to confidently expecting that AI will disrupt our economy, change work as we know it, and perhaps even change the evolutionary curve of our species…

Listen now

3 months ago · 15 likes · Nate

2025 AI Trends: A teardown of Mary Meeker’s epic 340 slide 2025 deck

Nate’s Substack

I Summarized Mary Meeker's Incredible 340 Page 2025 AI Trends Deck—Here's Mary's Take, My Response, and What You Can Learn

So Mary Meeker wrecked my weekend. She’s an incredible internet legend and she dropped a 340 slide report on AI (her first major public report in 5 years). I had to dig in…

3 months ago · 391 likes · 62 comments · Nate

2025 AI Trends Deep Dive: A deeper dive on the 2025 trend deck

Nate’s Substack

Mary Meeker AI Trends 2025 Deep Dive: 7 Unexpected Truths About AI's Next Phase

The discipline of talking out loud is very underrated. We say do it for interviews to practice. Do it for powerpoint presentations you don’t want to mess up. That’s all true. (It’s still hard to make yourself do it…

Listen now

3 months ago · 29 likes · 5 comments · Nate

LLMs and Jobs

I wrote posts pretty regularly on AI and the jobs situation.

The Kids will be OK: How to think about AI with kids.

Nate’s Substack

The Kids Will be Ok: How To Skip the Jobs AI Doom Spiral and Actually Prepare for the Age of AI: A Tech Career Manifesto

I think this is a debate our children will ultimately have to conclude (hence my illustration here), but we are the ones who have to start the conversation…

Listen now

3 months ago · 71 likes · 21 comments · Nate

The irreducible Human: What we bring as people in the age of AI.

Nate’s Substack

The Irreducible Human: Six Things We Still Do That Machines Can't

If you’ve been following my Substack for any length of time, you’ll be familiar with the concept of Polyani’s Paradox—the idea that work is more than we can speak. And if we can’t speak or describe what we actually do for work, then we won’t be able to tokenize it easily, and that puts it outside the baseball field for LLMs to automate away…

3 months ago · 27 likes · 24 comments · Nate

AI Resume Survival Guide: How to think about resumes in the age of AI.

Nate’s Substack

The AI Resume Survival Guide (for 2025 and Beyond)

I think I get a question about resumes on my TikTok just about every day. And mostly they boil down to three questions: 1) how do I talk about my AI experience on my resume?, 2) how do I responsibly use AI in creating my resume, and 3) what do I do about the AI checkers recruiters are using to catch resumes…

4 months ago · 137 likes · 17 comments · Nate

AI and jobs: A guide if you’re worried about AI and jobs.

Nate’s Substack

If You’re Worried AI Will Replace You, Read This First

I’ve written extensively about AI disrupting workflows, AI being used at leverage points in workflows, and are we tired of workflows yet? What the heck are workflows? How do they relate to jobs? What do I mean when I talk about tokenized workflows? That’s super vague…

4 months ago · 95 likes · 15 comments · Nate

AI and high performing teams: How high-performing teams are using AI.

Nate’s Substack

Your Team is Using AI Wrong: The Hidden Pattern Behind High-Performing AI Teams

I didn’t mean for this one to end up at 7200 words, promise. The truth is that team productivity is probably the biggest question swirling around AI and work right now—we see lots of anecdotal evidence that AI helps individuals but team gains are much more difficult to measure…

4 months ago · 36 likes · 13 comments · Nate

New Jobs in the AI age: What new jobs are opening up in the age of AI?

Nate’s Substack

Finishing What AI Starts: The New Jobs That Will Define the Next Decade

This is one of those in-depth posts, and I’m not going to apologize about that. Our jobs and future deserve nothing less. Bottom line: as AI scales I’m observing more and more obvious cracks in AI systems that not getting better, and there are entirely new job families that are incubating inside those spaces…

5 months ago · 55 likes · 5 comments · Nate

Obstetric Intelligence by an ObMD

Where to Start with LLM and AI? Read Nate's newsletters: