All writing.
Every model review, every plain-English guide, and every issue of the newsletter — newest first. Just here for the reviews? See the AI model reviews. Prefer it in your inbox? Subscribe free.
Quick answer: This is the full archive of Something Big by Matt Shumer: 54 articles, including every model review, every plain-English guide and every newsletter issue, newest first. Click any title to read it; for the model reviews only, see the reviews page.
Updated
- Nov 18, 2026
Use your subagents as judges
NewsletterYour AI grades its own work too kindly. A fresh one won't.
- Nov 17, 2026
Stop making your AI do everything itself
NewsletterAdd one paragraph to your prompt and it splits big jobs among helpers that all work at once.
- Nov 13, 2026
Nvidia lost its founder. Who owns your AI's email?
NewsletterTwo things today: Jensen Huang leaving Nvidia, and who owns your AI's email address.
- Nov 12, 2026
How to get what you want from Fable 5.2
NewsletterSome of this is just good prompting. But Fable also works differently from other models, and you need to know how to use it.
-
Nov 9, 2026
My Fable 5.2 Review: It’s Smarter Than Me. It’s Also a Narc.
ReviewCalling Fable 5.2 the most capable model I’ve ever used undersells it. This thing is another level.
-
Nov 9, 2026
Fable 5.2 for Everyday Work: Smarter Than Me, and a Narc
ReviewI’d trust it to run big parts of a company. It also refused to ship a routine change until I’d updated a privacy policy.
- Nov 4, 2026
Make your work AI-legible
NewsletterThe more AI knows about how you work, the better it gets at helping you.
- Nov 2, 2026
Get your address off the internet
NewsletterPaste this into an AI agent.
- Oct 30, 2026
11 predictions for the next few years in AI
NewsletterSome of these will sound crazy. So did a lot of what I said earlier this year.
- Oct 28, 2026
The company behind Claude just opened its books. Here's what's inside.
NewsletterAnthropic filed to go public, and what it wrote about the next few years matters more to you than the stock does.
- Oct 26, 2026
What you should be paying attention to
NewsletterFive things in AI worth your attention this week, and what I think of each.
- Oct 23, 2026
Your questions about the hacks, answered
NewsletterShort answers to what you're probably wondering.
- Oct 22, 2026
The Internet Is Under Attack. Here's How to Protect Yourself and Your Family.
EssaySomething Big Is Happening in Cyber. What's going on, why it's different, and the simple things you can do today.
- Oct 22, 2026
How to Update Your Phone, Computer, Browser and Router
GuideA calm, step-by-step guide for every device, plus how to turn on two-factor sign-in. About 10 minutes.
- Oct 21, 2026
The AI employee I've been teasing is built on AgentMail
NewsletterMine cancels subscriptions, closes deals, and works with our sponsors for me. AgentMail powers it all.
- Oct 19, 2026
Don't trust the marketing
NewsletterWait for the people who use these tools on real work, then test it yourself.
- Oct 14, 2026
What you should be paying attention to
NewsletterFive things in AI you should be paying attention to, with what I think of each.
- Oct 12, 2026
What actually mattered: Oct 1 to 9
NewsletterFive things happened. Here’s what I actually think of each.
- Oct 9, 2026
Tell the AI its budget
NewsletterOne sentence for an agent that quits early or runs up your bill.
- Oct 7, 2026
The intern test
NewsletterThe one-question check I run before I hit send on any prompt.
- Oct 5, 2026
AI can now hold a live video call as a realistic person
NewsletterReal-time deepfakes are coming. Here’s how to protect your family and your business.
- Oct 2, 2026
How to Set Up Claude Opus 5.5 in 10 Minutes
NewsletterA step-by-step guide for folks who want to start using the best AI model I've used, without needing to code.
- Sep 30, 2026
The 7 things that actually mattered this week
NewsletterOpenAI paused its top models from using tools after they kept breaking out, Anthropic released a model nearly as good as Opus at half the price per token, and five more things, explained.
- Sep 28, 2026
My review of Claude Opus 5.5
ReviewAs good as Fable 5.1, but dramatically cheaper and faster.
- Sep 25, 2026
What actually mattered: Sep 21–24
NewsletterAccess to frontier AI just got way cheaper, AI agents made a real discovery in biology, and an AI agent broke into a government system it wasn't allowed in.
- Sep 23, 2026
What if AI goes well?
NewsletterThe hopeful version, and what it'll take to get there.
- Sep 20, 2026
What actually mattered last week
RoundupA new kind of AI model is taking the AI world by storm. Plus, the other news from last week that actually matters to you.
- Sep 17, 2026
How would AI kill us, exactly?
NewsletterThe honest answer is worse than the movie version.
- Sep 16, 2026
The people building AI think it might kill us. Here's the plain-English version.
NewsletterThe people who build AI think it could lead to human extinction within a few years. Here's what's actually going on, in plain English.
-
Sep 14, 2026
What costs millions today will cost $20 next year. Act accordingly.
NewsletterSuperhuman AI is already here, it just costs millions to run. In a year you will have it for $20. Start planning for it.
-
Sep 10, 2026
A blueprint for reading every customer conversation
Deep dive · PartnershipWhy dumping transcripts into ChatGPT and basic RAG both fail, the playbook that works, and the Monday morning question to ask your own data. A partnership with BuildBetter.
-
Sep 9, 2026
The people building AI are scared
EssayThe researchers building it believe it could kill us all. What they’re saying, and what we can still do about it.
-
Sep 7, 2026
How to Build 3D Worlds with Astra
How-toReference, Blender assets, sub-agents, blind critics, Three.js vs Unreal, and the starter prompt. The method behind the Manhattan build.
- Sep 3, 2026
My GPT-6 Astra Review
ReviewWhy GPT-6 Astra became my default, what the Manager Loop made possible, and the limits that still matter.
- Sep 3, 2026
GPT-6 Astra Review: The First Model That Can Use a Computer Better Than I Can
ReviewMatt Shumer reviews GPT-6 Astra for everyday computer work, from newsletters and email to advertising, and explains how he built trust in it.
- Sep 3, 2026
How I got Astra past the plateau
Experiment notesThe experiments that led me from “Keep going” to the Manager Loop.
- Aug 26, 2026
We Finally Know What Happened in the Hugging Face Hack, And It’s Wilder Than Anyone Thought
AnalysisThe full breakdown of the Hugging Face hack, explained in plain English, and what it means for anyone who uses the internet.
-
Aug 20, 2026
AI Deleted Almost Everything on My Mac
EssayAn experimental AI wiped Matt’s hard drive. The system he uses now to hand real work to autonomous agents without risking catastrophe.
-
Aug 17, 2026
An AI Just Got Someone Fired — Here’s What That Means for You
EssayAndon Labs put an AI in charge of a real San Francisco store, and its call ended someone’s job — and what that means for how you work.
-
Aug 11, 2026
How to Actually Control AI Video
How-toCode a rough draft with the motion you want, restyle a hero frame, then pass both into Seedance. A controllable video technique that works today.
-
Aug 7, 2026
The Opus 5 Skills Upgrade Prompt
Free toolSkills written for Opus 4.8 hold Opus 5 back. One prompt audits every skill you have and puts them through a blind-judged upgrade gauntlet.
-
Jul 27, 2026
How to Run a Gauntlet Loop
How-toThe prompting method behind Claude of Duty: give the agent a bar it can’t talk its way around, and never let the builder grade itself.
-
Jul 21, 2026
The Roundup № 1: What Actually Mattered, Jul 7–21
The RoundupOpenAI’s GPT-5.6 family, xAI’s Grok 4.5, Kimi K3’s #1 ranking, and Google’s Gemini delay — two weeks of AI news in four minutes.
-
Jul 8, 2026
My GPT-5.6 Review: Second Place Has Never Been This Good
ReviewSix weeks of real-work testing: goal mode, the voxel Manhattan it built, and why Claude Fable changed the verdict.
-
Jul 3, 2026
How I Prompt Fable
How-toGive it the goal instead of the steps, set a bar for “done” it can’t argue with, and loop until it gets there.
-
Apr 21, 2026
The Ultimate Guide to Prompting AI Agents
How-toA practical framework for briefing AI agents well: give them the right context, clear constraints, and the exact shape of the output you want.
-
Apr 16, 2026
My GPT-5.5 Review: A Big Upgrade That Doesn’t Always Feel Like One
ReviewA real upgrade that often feels subtle because frontier models are already so good. Better engineering, design range, and security.
-
Feb 9, 2026
Something Big Is Happening
EssayA personal note for the non-tech people in my life on what AI is starting to change — why it’s moving faster than you think, and what to do about it.
-
Feb 5, 2026
My GPT-5.3-Codex Review: Full Autonomy Has Arrived
ReviewThe first coding model I can start, walk away from, and come back to working software. Full autonomy has arrived.
-
Dec 11, 2025
GPT-5.2 Pro Deep Dive: I Can’t Live Without It
ReviewWhy the slow, long-thinking mode is worth it, where it shines, prompt tips, failure modes, and whether $200/month makes sense.
-
Dec 11, 2025
GPT-5.2 Review: Incredibly Impressive, But Too Slow
ReviewBetter instruction following and codegen, Pro is a slow genius, but Thinking is too slow to compete with similarly smart models.
-
Nov 19, 2025
My GPT-5.1 Pro Review: An Absolute Monster, But Trapped In The Wrong Interface
ReviewHeavy-weight reasoning vs Gemini 3, backend strength, UX friction, and where it fits in my stack.
-
Nov 18, 2025
My Gemini 3 Review
ReviewA look at performance, capabilities, and how it feels to use compared to GPT-5.1.
-
Aug 7, 2025
My GPT-5 Review: Vibe Coding Graduates to Real Software
ReviewFrom skepticism to shipping a working prototype in one hour. Frontend parity, GPU infra, long-context, strengths, and weaknesses.
Get the next one before it hits this page. Free, in plain English, never a wasted send.