# The AI Engineer’s Creed — Full Metal Jacket Parody

AI engineers swear allegiance to their software factories in this Full Metal Jacket AI parody video.

Canonical URL: https://www.transitivebullsh.it/projects/the-ai-engineers-creed-full-metal-jacket-parody

Author: Travis Fischer

Published: 2026-10-17

Updated: 2026-10-17T15:51:00.000Z

Tags: AI, Video, Projects

[YouTube](<https://www.youtube.com/watch?v=GT9zYmPhSys>)

[Source](<https://github.com/transitive-bullshit/my-software-factory>)

![The AI Engineer’s Creed — Full Metal Jacket Parody](<https://assets.cultural-alignment.com/personal-site/media/eb1004e73d20e17cff85dceb100956995172f3505bfb257bee18530dc320a28b.jpg>)

[Watch video](<https://assets.cultural-alignment.com/ai-engineers-creed/6ff14cd31eb6ce12b78239eec3347ce08cc04ba6ddf0c80655b42377bb2e8ff7.mp4>)

The AI Engineer’s Creed: A parody of the famous scene from Full Metal Jacket (1987).

<a id="1741fefdca6144d89a2ad7c3175f51c0"></a>

## Motivation

Every AI engineer I know is building some version of the same thing right now: a personal software factory, where agents write more code than any human could possibly review. At some point it stopped feeling like a workflow and started feeling like a creed.

And no, I don’t want to see your software factory. 😂

So I recast the most famous creed in film: the barracks scene from [*Full Metal Jacket*](<https://en.wikipedia.org/wiki/Full_Metal_Jacket>) *(1987)*, where the recruits recite their creed to their rifles before lights out. In my version the rifle is your agent, the recruits are the AI engineers I interact with the most on X, and the drill instructor is [Jensen Huang](<https://x.com/JensenHuang>), the man who coined “AI factories”, in a leather jacket instead of a uniform.

[Watch video](<https://youtu.be/nkGIxGdZoYY?t=34>)

The original: the barracks creed scene from Full Metal Jacket (PG version).

[Matt Pocock](<https://x.com/mattpocockuk>) delivers the hook, [Peter Steinberger](<https://x.com/steipete>) holds the line in the wides, [swyx](<https://x.com/swyx>) (who coined “AI engineer”) gets to chant it in his own close-up, [Simon Willison](<https://x.com/simonw>) stands fire watch and gets the last word, and [poteto](<https://x.com/poteto>)’s avatar hangs on the office wall as the “PRs” poster.

<a id="b8a5a05b079842a5a36366a42a63f90e"></a>

## How it was made

The whole thing came out of one long collaboration with Claude Code (Opus 5.5): it wrote the scripts and review pages, and I reviewed every round on them and sent back notes.

- **Script:** every parody line is locked to the original line’s start and end, within two syllables, so the new words land on the same beats as the film.
- **Voices:** the recruits’ creed is a single sung take from Eleven Music, cut at its pauses, so the crowd sounds like one platoon. Jensen’s orders are a Fish Audio clone of his voice, built from ten minutes of clean interview audio. The fire watch is an ElevenLabs designed voice.
- **Shots:** every shot is regenerated: Nano Banana Pro keyframes built from character sheets of real headshots, animated with H3 Max with each line’s audio pinned, then lip-synced again wherever the mouth didn’t sell it.
- **Title, captions, and credits:** rendered locally in HyperFrames, with every caption word force-aligned to the vocals and lit as it’s sung.

I also tried a second direction, lip-syncing the cast onto the original footage, and dropped it: the fully generative cut is the project.

![Matt’s character sheet: real headshots in, consistent likeness out.](<https://assets.cultural-alignment.com/personal-site/media/2dcf5a6100967fc52060d947432dcc372670f195db3d3431ee748786617f7938.jpg>)

Matt’s character sheet: real headshots in, consistent likeness out.

<a id="3cc30e65d92c46f0b3dca6e150753b37"></a>

## Key decisions and lessons

- **The McGurk effect:** or what you see changes what you hear**.** Jensen’s opening “PROMPT!” kept sounding like “PRONT!” even though the isolated audio was perfect. It turns out this was because the generated mouth never closed for the M and P. This was so surprising to me that [I created a write and explainer video here](<https://www.transitivebullsh.it/projects/the-mcgurk-effect>). The fix was a new lip sync over the exact same audio.
- **Pin both ends of a shot.** Every H3 prompt pushed the camera in until I anchored each shot’s last frame to its keyframe too. H3 also renders its frames about 2.5% wider than the keyframe it starts on, which snapped visibly in the first few frames; exact 16:9 keyframes and holding the first and last frames fixed it.
- **Small faces need help.** The fire watch’s face is about 100 pixels tall under a helmet, and two lip sync models passed it through untouched. Lip-syncing an upscaled crop of the shot, then blending back only the mouth and jaw, finally got him to say his line.
- **Never re-time generated audio.** Stretching a read to fit always sounds worse than regenerating it, so every take is placed whole.
- **Measure the captions, don’t eyeball them.** Whisper’s word times run early after pauses, so the captions are force-aligned against the separated vocals and checked against the finished mix: line starts land within 25 ms of the voice.

![Captions in the video’s own style: each word lights up gold as it’s sung. Scene featuring swyx.](<https://assets.cultural-alignment.com/personal-site/media/91eb52a7b5802fcdb0c79f785eb245f04f7bf7c0aa509931943fe44bbebfef92.jpg>)

Captions in the video’s own style: each word lights up gold as it’s sung. Scene featuring [swyx](<https://x.com/swyx>).

<a id="492ba56b527446358621cc317ff98066"></a>

## Cost

A 76-second, fully AI-made parody with a title card, word-timed captions, and end credits for the cast. It took 117 fal generations (**about $97**) and a lot of review rounds.

<a id="2f40c67b6d95490fba3e0206013b72ce"></a>

## Tools

- [Claude Code](<https://claude.com/product/claude-code>) with [Claude Opus 5.5](<https://www.anthropic.com/claude/opus>): planning, scripts, review pages, and every render
- [Nano Banana Pro](<https://fal.ai/models/fal-ai/nano-banana-pro/edit>): character sheets and keyframes
- [H3 Max](<https://fal.ai/models/minimax/h3-max/image-to-video>): animation, with each line’s audio pinned
- [H3 Max Lip Sync](<https://fal.ai/models/minimax/h3-max/lip-sync/video-to-video>) and [Sync-3](<https://fal.ai/models/fal-ai/sync-lipsync/v3>): lip sync passes
- [Eleven Music](<https://elevenlabs.io/music>): the recruits’ chorus creed
- [ElevenLabs Voice Design](<https://elevenlabs.io/voice-design>): the fire watch guard’s voice
- [Fish Audio](<https://fish.audio/>): Jensen’s voice clone
- [HyperFrames](<https://hyperframes.heygen.com/>): title card, captions, and end credits
- [fal](<https://fal.ai/>): hosts the image and video models

<a id="330f93f8472c435cad65b148da82994a"></a>

## Credits

- [Jensen Huang](<https://x.com/JensenHuang>) as the drill instructor
- [Matt Pocock](<https://x.com/mattpocockuk>) as the recruit with the hook and the first close-up
- [Peter Steinberger](<https://x.com/steipete>) as the second recruit
- [Shawn Wang (swyx)](<https://x.com/swyx>) as the third recruit
- [Simon Willison](<https://x.com/simonw>) as the fire watch guard
- [Lauren Tan (poteto)](<https://x.com/poteto>) on the “PRs” poster
