Four prompts, same chat, in order. The third one puts two versions of your next five years side by side: one where your habits stay the same, one where you change the pattern it thinks is holding you back. It can't tell your future. It compares two paths using what you have already told it about yourself. 1. Five things it suspects about you, evidence separated from guesses 2. The patterns in how you think and decide, and what you might be avoiding 3. Two versions of your next five years, side by side 4. A short paragraph to read every morning, with one action for today Some of it will be wrong. Push back on anything that does not sound like you.

I ran a real test: OpenAI's GPT-6 Astra against Anthropic's Fable 5.1. Same skill, same prompt, no assets handed over. Neither one got my HeyGen avatar, my ElevenLabs voice, or any footage. Each had to go get all of it itself — find my avatar, pull my voice clone, do its own research, grab its own B-roll and screenshots, and edit the finished video start to finish. Here's the exact prompt I gave both of them: --------------- I need you to take me from idea to a finished Reels video. I want you to create an engaging and professional video about GPT-6 Astra. You need to use Tom Lyons voice clone and a HeyGen avatar. Start the video off by telling everyone this is not Tom and that you orchestrated the entire video. You planned it out, you researched it, you grabbed all the B-roll, you grabbed the screenshots, you edited everything, and you produced the finished video—which is why they're watching it right now. I want this to feel professional, like it was edited by a human using Hyperframes. Do not give me a draft or a POC; give me a finished, working version that I can post on my Reels channel. I've put the skill used in Cloud Code for creating the styles that we normally use in the folder. So, take what you can from that to help you produce what you need. --------------- The skill both of them used: **the real Commander Tom production skill, made safe to share** — the show bible, the motion-graphics engine, and a step-by-step guide to running the same challenge yourself. Watch the video, then try the prompt yourself and tell me which one you'd have picked.

Quick one for anyone using Claude for real work: it will lie to you and never tell you it's happening. Every chat has a context window, basically how much it can hold in its head at once. Go past it and the session starts to degrade, that's exactly when it starts hallucinating and making things up. Claude never flags this. Fix: give it a canary. Tell it, "Always start your replies with my name, and save that instruction to memory." Put the same line in any instruction file you use too. Now you've got a tell. The moment it stops using your name, you know the session's degraded. Close it, start fresh, keep going. Video's attached if you want to see it set up start to finish. Anyone else running into this?

Opus 5 is the best model on the board and it talks like a consultant who bills by the syllable. Long answers, technical words, and you pay a token for every one of them. Anthropic already published the fix. It is an output style, it takes about sixty seconds, and most people have never opened the setting. Two things in the video: 1. The output style. Set once, changes how Claude talks to you forever. Mine is ELI5 plus one line of ASD-STE100 Simplified Technical English, which is the standard aircraft manufacturers use so a mechanic in any country can read a repair manual safely. 2. Skills for length. Do not hard-wire “be brief” into your style, because some days you need the long version. Put it on a switch instead. /bro rewrites the last answer in plain English. /quick 3 gives you the three things that mattered. One thing worth knowing: do not put these rules in CLAUDE.md. That file is read once at the top of a session and then slides behind you. An output style is written into the core system prompt and Claude Code keeps reminding itself about it mid-session. Same rule, two places, and only one of them still works at turn ninety. Credit where it is due: the ELI5 output style is Lydia Hallie at Anthropic. The ASD-STE100 line is Andrew Carr. The file that installs all of it is attached. Hand it to Claude Code and tell it what you want.

I made a video of a version of me that I never filmed. Commander Tom, a clone of me from the year 3192, standing in the engine room of a starship, talking. The face is mine, the voice is mine, and everything else is generated. People asked how it was made, so I recorded the whole thing and wrote the guide to go with it. Both are here. The build is three ingredients: photos of your face, a scene to put that face into, and audio. Five steps end to end. Shoot a photo set. Several angles, several expressions, and one clean forward-facing shot, which is the one that does most of the work later. Generate the scene with Nano Banana Pro inside PromptEdit. My exact scene prompt is in the guide. Swap your real face onto that scene. This is a second pass and it is the step people skip. The first render gives you a plausible person who is not quite you. My face-swap prompt is in the guide too. Make the audio. Record yourself, or clone your voice in ElevenLabs from about five minutes of recording. The audio has to exist before you animate, because the animation is driven by it. Animate with HeyGen Avatar 4, also inside PromptEdit. 720, 9:16, generate. What the run in the video actually cost, at 5 cents a credit: About 3 credits an image, so roughly 15 cents a shot 66 credits for the animation, which is $3.30 Two images plus one animation, so about $3.60 PromptEdit has no subscription, you buy credits and spend what the job costs. ElevenLabs is separate and I do not quote its pricing, so check their current rates. The guide has both prompts in copy-paste blocks, a cost table, nine things that go wrong with what to do about each, and a one-page checklist. If you build one, post it here. I want to see them.