Joined August 2022
- Tweets 266
- Following 503
- Followers 5,551
- Likes 3,439
56 Photos and videos
Apr 28
Vibe coded some custom interfaces with the Push 2 using Claude.
I gave it some references, creative direction and a good environment to develop and test midi integrations and it ran with it.
31
40
632
36,016
Spencer Sterling retweeted
Apr 17
Jamming with @cerspense on Sentinel. Built a 3D scene of points and lines, fed it through SDXL to turn it into jellyfish, layered a particle ripple system on top, finished with film grain. Everything vibe coded with Claude in real time. We described what we wanted as we listened to the music and just watched it come together.
6
26
1,083
Apr 14
Testing out audio reactivity and vibecodable shader modules in Sentinel. Describe an effect, Claude builds the node and tests it via mcp.
Stack it with real-time SDXL and you get this!
More on how this works below.
18
27
252
12,059
Apr 14
It can easily integrate complex data types into real-time graphics like mapping facial landmarks to geometry. Audioreactivity in this example is driven by an external program over OSC
2
737
Apr 14
Sentinel has an MCP server that lets Claude configure and build real-time interactive graphics nodes and test them end to end within the environment. It can build shader modules that take in arbitrary data and pixels and output whatever you want in real-time
7
814
Apr 9
Dialing in real time V2V in Sentinel.
No Python or venvs, just an installer. Runs locally on any 16GB NVIDIA GPU.
Sign up for early access: ood-labs.com/sentinel/waitli…
42
89
815
57,560
Mar 31
Never been able to explore latent space like this before..
👀
49
66
992
79,026
Spencer Sterling retweeted
Mar 9
@cerspense has been developing a tool (Sentinel) that allows live diffusion.
I have been playing with it in conjunction with TouchDesigner (for audio reactivity) and my Teenage Engineering OP-XY (for additional effects trigger).
Being able to make animations on the fly based on a song feels like playing an instrument that makes visuals instead of sounds. It is awesome!
This has been made possible thanks to my Dell Pro Max T2 tower equipped with an NVIDIA RTX PRO GPU (you can check out the spec here: lnkd.in/gQ-S9cF3).
#DellProPrecision #DellTech #NVIDIA
6
6
59
2,152
Mar 6
This is what directing an AI creative studio looks like.
I gave my orchestration system a reference image and had it deploy three different interpretations across three machines running Blender simultaneously, all visible from a single dashboard.
When one direction looks promising, I branch from it. The system copies the files to the other machines and keeps exploring from that new starting point. Branch, direct, branch again. Each split opens up a new creative path while I give notes in real-time.
The number of creative directions I can explore simultaneously is only limited by how many computers I have.
58
82
860
84,865
Feb 25
A few weeks ago I gave Opus 4.6 a pack of stage assets in Unreal Engine, had it analyze all the example levels, then told it to build a stage.
It assembled the whole thing, checked its own work from multiple camera angles, and when I gave it notes (trusses too short, stairs clipping through a crowd barrier) it fixed everything autonomously.
It's gotten a lot better since then
18
32
375
24,925
Feb 23
I built an agentic system that taught itself the Blender donut tutorial by watching it on YouTube.
It watched the tutorials, extracted the steps, filled in the gaps in own tooling and completed the entire thing autonomously.
132
205
2,181
253,932
@cerspense cranked out some @Alibaba_Wan Wan loops for @FLOSSTRADAMUS with @ComfyUI - at @Themidwaysf - 🤳🏽@Machinedelusion
1
2
12
2,240
12 Sep 2025
Got to try @krea_ai's new Realtime video with my laser setup! Creating content on the fly is a gamechanger for live events. Instead of prepping terabytes of loops I can just vibe and respond to the music and audience in real time
7
2
24
2,388
12 Sep 2025
Compared to StreamDiffusion, it seems to have a lot more temporal consistency, but it lacks some responsiveness in the input, making it less ideal for live camera/video input. It feels like its making the video in chunks vs frame by frame and seems to struggle to match the motion in the input video especially with faster movements and multiple subjects. Overall very pleased to have a new kind of realtime model to play with!
4
1,111
12 Sep 2025
In this setup, I'm feeding in a live screen capture capture of me playing around with 3D models in Sketchfab into Krea, capturing that with TouchDesigner and Notch for realtime FX and laser tracing
2
1,005
