iPhone Mirror
Shows your iPhone’s screen live on your Mac, inside Apple’s iPhone 17 Pro frame, over one USB cable.
Get the code
AI FOR MORTALS.
Your daily AI edge that will make everyone wonder how you do it all.
Every weekday, the practical AI updates that matter, and exactly what to do with them.
The latest in AI, in plain English. Free, every weekday.
How I Built a Murder Mystery Game With a Team of Claude Agents
Pat Simmons
Are Your Long Claude Prompts Worth It? We Cut Them Down to Find Out
AI for Mortals Staff
How to Make and Edit PDFs, Docs and Sheets in Gemini Without Leaving the Chat
Gemini can now build a PDF, Google Doc, spreadsheet or slide deck and let you fix it right in the chat. Here's how to use it, what works on your phone, and what to check before you send the file.
AI for Mortals Staff
Recent stories
Gemini Can Now Edit the Files It Makes for You
Pat Simmons
OpenAI Doubles Usage on ChatGPT Pro Plans
Pat Simmons
Canva Launches Brush, an AI That Edits Your Designs
Pat Simmons
ElevenLabs Sound Effects v3, Tested Against v2
AI for Mortals Staff
How to Teach Claude Your Writing Style From Your Own Edits
AI for Mortals Staff
Damon Mobile
Murmur
Google Unveils Gemini 4 Carbon, and Security Teams Get It First
Google's strongest model yet is built for long jobs that run for days and is meant to admit what it can't back up. Only a small group of cybersecurity teams can use it for now, with no date for everyone else.
Chrome Can Now Fill In Forms With Details From Your Gmail
If you've let Gemini into your Gmail, Chrome's autofill menu now suggests flight bookings, order numbers and tracking info pulled from your inbox as you fill out a form. Here's how it works and how to control what it reads.
You Can Now Text Your ChatGPT Dot
OpenAI's always-on Dot now lives in your phone's messages app over iMessage or RCS. Send it a task as a text, photo or voice note, and it texts you back on its own when something needs you.
Firefox Can Now Fill In Forms From Your Open Tabs
Firefox's Smart Window can now suggest answers for a web form using tabs you pick, like your LinkedIn page for a job application, and watch up to five pages for a sale or a new job listing.
Cloning morphowater.com, pixel for pixel
A rebuild of the morphowater.com product site with its 3D can and scroll motion, using no assets taken from the original, following my clone-app-pat-pro playbook.
Kimi K3.1 Pro
Opus 5.5- Fable 5.1
GPT-6 Astra
DeepSeek V4.1 Flash
A first-person billiards game
A first-person 3D billiards game in the browser with real ball physics, a computer opponent and shot-by-shot replay, set in a photoreal pool bar.
- Kimi K3.1 Pro
- Opus 5.5
- Fable 5.1
- GPT-6 Astra
- DeepSeek V4.1 Flash
Cloning oryzo.ai, pixel for pixel
A rebuild of the oryzo.ai site with its 3D and motion, using no assets taken from the original.
Gemini 4 Argon- Opus 5.5
- Fable 5.1
- GPT-6 Astra
A Rocket League style car soccer game
A playable car soccer game in the browser with photoreal graphics and a computer opponent.
- Gemini 4 Argon
- Opus 5.5
- Fable 5.1
- GPT-6 Astra
A product launch video
A 30 to 60 second launch video for the same coffee brand, with photoreal product shots and sound.
- Gemini 4 Argon
- Opus 5.5
- Fable 5.1
- GPT-6 Astra
Kimi K3.1: No Hype Full Review & Testing (Best Open Weight Model?)
Watch on YouTubeSkills
Teach your agent a new job.
Instruction packs I built so Claude Code and Codex can do real work: clone an app, edit in Premiere, build in Blender. Free to install.
Browse all 7 skills
Clone App Pat ProGive it a URL and it rebuilds that web app in code, then measures the copy against the original.
Blender ProductionLets an AI agent build, render and visually check Blender projects through Python and MCP.
Unreal Agent HarnessLets Claude Code build and play 3D cities in Unreal Engine 5.8 through the official Unreal MCP plugin.
Fable OrchestrationUses Claude Fable 5 as the planner and Opus 4.8 as the builder, so you pay the top rate only for the planning.
Astra Premiere EditingTeaches an AI agent to edit video in the real Adobe Premiere Pro app, the way a person clicks through it.
Seedance Prompt BuilderTurns a plain-English video idea into a ready-to-paste prompt for the Seedance 2.0 video model.
Kimi K3.1 Pro: No-Hype Full Review & Testing
- Kimi K3.1 Pro
- Opus 5.5
- Fable 5.1
- GPT-6 Astra
- DeepSeek V4.1 Flash
Moonshot's new model is officially out, so I ran it through four hard builds against Opus 5.5, Fable 5.1, GPT-6 Astra and DeepSeek V4.1 Flash.
Gemini 4 Argon: No-Hype Full Review & Testing
- Gemini 4 Argon
- Opus 5.5
- Fable 5.1
- GPT-6 Astra
Google released Gemini 4 Argon, so I ran it through four hard builds against Opus 5.5, Fable 5.1 and GPT-6 Astra and tracked what each one cost.
AI Video Editing in Premiere Pro: How Claude Opus 5.5 Does 95% of My Edit (and How GPT-6 Astra Compares)
- Opus 5.5
- GPT-6 Astra
How I turned Opus 5.5 into my personal video editor: it edits every take inside Premiere Pro on a Mac Mini while I record the next one. The skill and the Premiere Pro bridge are free on GitHub.
Claude Haiku 5.5: What It Costs and How It Scores Against Sonnet 5.5 and GPT-6 Luna
- Haiku 5.5
- Sonnet 5.5
- GPT-6 Luna
- Haiku 4.5
Anthropic's smallest Claude model costs a tenth of Haiku 4.5's price on the API, is free to pick in the Claude app, and beats GPT-6 Luna in Anthropic's own tests while trailing Sonnet 5.5.
CapCut's Video Editor Is Coming to ChatGPT
CapCut is bringing its video editing and generation tools into ChatGPT, where you build a first draft from an idea or your own clips and keep editing it by asking. The open beta lands in November, and an early version already works in ChatGPT's desktop app.
Use AI to Decompile Any App or Game
People are putting skateboarding inside Call of Duty and Minecraft inside Elden Ring. Most of it comes down to decompiling. Here is what that means, what is legal, and the exact prompts to do it yourself.
Google Launches Playground for Making Games
Google launched Playground, an experimental site where you describe a game in plain words and get one you can play in your browser, free for adults in the US.
Google's Nano Banana 2.1 Arrives in Gemini and Search
Google released Nano Banana 2.1, the new version of the AI that makes and edits pictures in the Gemini app, and it's rolling out in Gemini and in Google Search's AI Mode.