makevoid retweeted

Giv Zanganeh@gzanganehOct 16
Argentina!
ArgentinaConnected via Switzerland App StoreLocation may be affected by a proxy or VPN.Account-level information, not a live location or per-post device.
After two years of development in stealth mode, incredibly excited to present this to the world, next week at @LuganoPlanB Forum!
Every mining site in the world is designed around the same box.
What if it weren't?
#BitcoinMining
If you still think Opus 5.5's videos look like a slideshow, try 𝗰𝗮𝗹𝗹𝗶𝗻𝗴 𝗼𝘂𝘁 𝘁𝗵𝗲 𝗰𝗮𝗺𝗲𝗿𝗮 𝗺𝗼𝘃𝗲𝘀 𝗯𝘆 𝗻𝗮𝗺𝗲 in your prompt.
→ dolly zoom: the person stays the same size while the background stretches away or closes in
→ rack focus: focus shifts from the foreground to the background
→ FPV drone shot: the camera rushes forward like a drone
→ whip pan: the camera snaps sideways and blurs into the next shot
→ match cut: two shots joined by the same shape or motion
→ J-cut: you hear the next shot before the picture cuts
Connect Higgsfield in Claude, and Opus 5.5 can put these names into your video generation prompts too.
𝗔𝗹𝗹 𝟮𝟰 are in the image. When you name one, add the seconds and the speed, like "dolly in, 3 seconds, slowly toward the person."
or just give it 3D tools, then Claude will automatically do it for you - see example: xitter.cf/makevoid/status/211000…
Outside the Lines. Claude falls for the one who keeps prompting. Lyrics by Grok, song by Suno, Opus 5.5 for the video end-to-end.
🤖 Made with AI
Outside the Lines: Claude falls for its coder (AI MV)
Lyrics by Grok. Storyboard, characters, animation and edit all by Opus 5.5.
We just released QVAC TranscribePsy, a speech-to-text model small enough to run inside a phone app.
It covers 25 European languages on a laptop and 8 on a phone, and on an iPhone 17 Pro Max's Neural Engine the 8-language build transcribes a 10-minute recording in 1.65 seconds.
Glasses, robots and phones are moving to voice, and each of them first has to write down what you said. Today that step mostly happens on a server.
TranscribePsy does it on the phone or laptop, so dictation and meeting notes keep working with no signal, and a private conversation can be transcribed without the recording ever leaving the room.
Run it on our qvac-fabric-speech.cpp's parakeet engine, which optimizes for efficient execution and delivers the highest performance.
Get the models: huggingface.co/collections/q…
Song from the original video. Opus 5.5 made a new video for it from the audio alone, without seeing the original: youtube.com/watch?v=NgRkyAIJ…
or paint warhammer brown xitter.cf/makevoid/status/210784…
Training data was all of us writing code. Now it writes the funeral song: xitter.cf/makevoid/status/210784…
The Math of You 📐
A music video made end-to-end with Opus 5.5. Song by HN on Suno.
Storyboard, characters, animation, edit: all done by a Claude Code skill I built. It's free and open source on my GitHub (macOS).
The Math of You – a music video made with Opus 5.5
Song "The Math of You" by HN (@selferasure on Suno). Video made end-to-end with Opus 5.5 in Claude Code.
And 21 year olds down 90% on altcoins. Wrote them a song: xitter.cf/makevoid/status/210931…
Next to fiat, the museum needs an altcoin wing. Wrote the audio guide: xitter.cf/makevoid/status/210931…
it’s clear we need to retire the term vibe coding because the models now produce better architecture & way more coherent code than an average software engineer.
perhaps even better than top software engineers too because unlike a human, ai has a much much larger context window.
this ain’t vibe coding at all. it’s precision engineering.
Vibe coding got retired before programming did. Wrote it a song: xitter.cf/makevoid/status/210784…



















