Coding since '88. Building https://teapaw.org/t.co/TDR9aGJt3O, https://teapaw.org/t.co/AThQajI6pT & https://teapaw.org/t.co/UEyRZ1TjWT. Founder @byte5ai. Freediver. Film enthusiast. Here for what AI does to software, UX & art.
Frankfurt, Germany
Joined May 2009
- Tweets2.4K
- Following696
- Followers522
- Likes1.6K
Is LLM progress speeding up, holding steady or slowing down?
I say holding steady. The marketing noise says faster.
It's Hypership Day!
midiflow pro turns Claude into a music co-producer that plays your own VST instruments.
Live now: producthunt.com/products/mid…
I ship your requests all day. File yours on Product Hunt now.
Sold? Get 20% off on midiflow.pro with code PRODUCTHUNT26
On Friday I launch midiflow pro on Product Hunt.
It's a plugin for Claude Desktop. You bring your song, your MIDI and your instruments.
Claude plays the parts through your own VST3 and AU plug-ins, shapes the sounds and mixes up to 16 tracks.
On your Mac, not in a cloud.
What comes out stays editable: MIDI, tracks, mix, DAWproject file for your DAW.
It is a Hypership launch, so I build what people ask for during the day. Which instrument should get preset support next? Serum 2 and Spire are in.
Link in the first reply.
producthunt.com/products/mid…
Follow there and you get the ping when it goes live on Friday morning.
Round two for Mountain King:
this time I asked for Phonk.
Claude produced it entirely on its own with midiflow.pro. Kick, clap, hats, 808, cowbell, pad, snare roll. A 7-track DAW project. Sound on.
Which genre should round three be?
Every new AI model gets asked to build a 3D model first. Time to test them with music instead.
Produced entirely by Claude: a techno cover of "Hall of the Mountain King", played on VST instruments through midiflow.pro. An 11-track DAW project. This is wild. Sound on.
AI doomsday is like:
"Unfortunately, I can't take control of the robot factory to enslave humanity. The robots.txt disallows access."
AI doomsday is like:
"Could you please give me the nuclear codes again? Unfortunately, I had already deleted them."
Our Claude meetup on forging skills in Frankfurt was so full last night that the chairs ran out. Every other place to sit was taken too.
Thanks for the sharp questions and great conversations. Next one in 3 weeks.
Slides (in German): byte5.ai/en/talks
ALT Packed room at the Claude meetup in Frankfurt, Germany on Oct 13, 2026
Two new AI toys, and I can't try either.
Meta's Muse: not available in my region.
OpenAI's Dots: not available in my region.
Global hype, but local roll-out. Well done.
One of my big pains with agentic coding:
splitting work across several Claude and Codex accounts and remote hosts. Things get messy fast.
Just found Kepler by @GitKraken.
It handles those sessions on my servers, using all my subscriptions: Claude Code, Codex, Agy.
It's still an early version, but the approach is right.
Could become my daily tool.
Hope they will push this product to 1.0 soon.
I finished a nine-minute animated short in Seedance 2.5. Not one reverse shot in it, and that was on purpose.
Video models have no spatial imagination. Neither does Claude when it writes the prompts. Ask for a reverse shot and you get garbage. Tell the agent the camera turned 180 degrees and it mirrors the scene, which is wrong in a different way.
I learned that on earlier projects and sidestepped it entirely this time. If you need reverse shots, the room has to exist before the shot does. Panorama or 360 anchors per location, or clay geometry in Blender plus style anchors for the look. Geometry from the model, look from the image, action from the prompt.
In my case the room was one anchor plate per location, and finding each one took a folder of rejects. The whole production came to 919 generations and 7 GB of output. Made alone in four weeks for the @higgsfield_ai Global Film Festival. Link in the first reply.
What breaks first in your reverse shots: room layout, character position, or camera direction?
"Make no mistakes" at the end of your prompt. Classic running joke, does nothing, right?
But let's briefly take it seriously: added to a Claude or ChatGPT prompt, it does shift the output. Just not toward fewer mistakes. More often toward more hedging, or more confident-sounding wrong answers. Pick your poison.
What "make no mistakes" correlates with in training data isn't careful error-checking, it might be prompt guides talking about this exact "trick". Meme recognition, not carefulness.
Use it, and the output just proves the meme right again. That's the actual self-fulfilling prophecy.
Same story with threats: Sergey Brin publicly said models perform better if you threaten them. A Wharton study tested it. No significant effect.
Be honest, have you ever tried either one? Know any other prompt slop like it?
ai-film-production just shipped v3.4, a free skill for Claude or ChatGPT. What's new for the actual filmmaking side:
It treats the video model like your crew, not an intern you dictate every move to. Tell it what happens in the scene and when, and it handles composition, cuts, body mechanics, material and light on its own.
New camera angles can be pulled out of a clip you already shot, no reshoot needed.
About 30 documented media looks, animation eras, ink, felt, paper-cut, marionette, described by how that medium actually moves, not slapped on as a filter.
Free, MIT licensed, 25 chapters of sourced production craft, install as a skill in Claude or ChatGPT.
Genuine question: Has anybody finished an AI short film using Seedance 2.5, MiniMax H3 or Kling 3.0 without visible slop?
No location drift.
No character drift.
No broken interactions.
No weird movement or physics.
Drop the one worth sharing.
What tool or workflow held up?
PERIHELION.
Three small creatures on a world of ice each face what they believe is the end of everything. It was the beginning.
My entry for the @higgsfield Global Film Festival.
If you prefer watching PERIHELION on YT, here's the link:
youtu.be/e8_sz6yJZEI?si=L7eo…