Build a balloon-camel simulator for an LED Burning Man totem
I'm making a LED Camel Totem for Burning Man. Task: I'm making a LED Camel Totem for Burning Man. I had the idea to make a Koons-style balloon animal.I explored this idea with ChatGPT, asking it to make some reference images. I also asked for some prompt generation. I have weak sketching abilities (it's on my list to improve), so this is how I "storyboard".To be cheeky, I asked Claude to make balloon simulator from which I could eventually drop into Fusion360 to muck with and 3D print. CamelKoons was born! [1]I wanted a Golang backend and web frontend. Fable pretty much one-shotted the step-one scaffolding: Golang physical simulation of a single balloon, streaming geometry to a Web application. Vibed through various issues and then step two was multiple balloons with twists (which were just choke points).In the world of disposable, hyper-focused software, this tool remained static to Dromedary Camel topologies. A generalized topology feature is left as an exercise for the reader's LLM.I like empowering my agents to loop [2]. So, I used Claude-in-Chrome to do some loops where Claude positioned the Camel and could screenshot it. I also gave it an HTTP endpoint to position the camera for itself and me.Eventually, I wanted to push views and comments from the Web page, so I added a comment box. Claude Code used its new-to-me "monitoring" feature to watch for that action and react to it in the session. Claude made itself a "look-at-camel" skill, so cute! [3]While the balloons were looking interesting, I noted it wasn't very Koons-like and Claude reminded me that Koons was art and we were doing physical simulation. So then we started distorting the physical model. Of course we also added model export, etc.After tokenmaxxing, I ended up with something that was a cross between a poop emoji and an alien dildo.I'm now learning the Forms feature in Fusion360 and following a great balloon-dog tutorial on YouTube. I think this guitar approach will win out over my Guitar Hero approach.[1] https://github.com/cameltopia/CamelKoons[2] https://github.com/ConAcademy/WeaselToonCadova[3] https://github.com/Cameltopia/CamelKoons/blob/main/.claude/s...; tools: Claude Code, ChatGPT, Claude in Chrome. Human role: The original post does not say how a person stayed involved.; limitations: The simulation software is hyper-focused and lacks generalized topology features, limiting reuse for other shapes. The author noted a disconnect between physical simulation and artistic intent, requiring manual intervention in Fusion360. Source reliability is anecdotal, with no evidence of successful final fabrication or measured time savings..
Tools
Published on Agent Work Atlas:
Overview
I'm making a LED Camel Totem for Burning Man.
Workflow
I'm making a LED Camel Totem for Burning Man. I had the idea to make a Koons-style balloon animal.I explored this idea with ChatGPT, asking it to make some reference images. I also asked for some prompt generation. I have weak sketching abilities (it's on my list to improve), so this is how I "storyboard".To be cheeky, I asked Claude to make balloon simulator from which I could eventually drop into Fusion360 to muck with and 3D print. CamelKoons was born! [1]I wanted a Golang backend and web frontend. Fable pretty much one-shotted the step-one scaffolding: Golang physical simulation of a single balloon, streaming geometry to a Web application. Vibed through various issues and then step two was multiple balloons with twists (which were just choke points).In the world of disposable, hyper-focused software, this tool remained static to Dromedary Camel topologies. A generalized topology feature is left as an exercise for the reader's LLM.I like empowering my agents to loop [2]. So, I used Claude-in-Chrome to do some loops where Claude positioned the Camel and could screenshot it. I also gave it an HTTP endpoint to position the camera for itself and me.Eventually, I wanted to push views and comments from the Web page, so I added a comment box. Claude Code used its new-to-me "monitoring" feature to watch for that action and react to it in the session. Claude made itself a "look-at-camel" skill, so cute! [3]While the balloons were looking interesting, I noted it wasn't very Koons-like and Claude reminded me that Koons was art and we were doing physical simulation. So then we started distorting the physical model. Of course we also added model export, etc.After tokenmaxxing, I ended up with something that was a cross between a poop emoji and an alien dildo.I'm now learning the Forms feature in Fusion360 and following a great balloon-dog tutorial on YouTube. I think this guitar approach will win out over my Guitar Hero approach.[1] https://github.com/cameltopia/CamelKoons[2] https://github.com/ConAcademy/WeaselToonCadova[3] https://github.com/Cameltopia/CamelKoons/blob/main/.claude/s...
Reported result
The workflow produced a functional but aesthetically flawed simulation, described by the author as resembling a 'poop emoji and an alien dildo' rather than the intended Koons style. The tool remained static to specific camel topologies, requiring manual distortion of the physical model to approach the artistic goal. No quantitative metrics on efficiency or final print success were reported.
Human role
The original post does not say how a person stayed involved.
Limitations
The simulation software is hyper-focused and lacks generalized topology features, limiting reuse for other shapes. The author noted a disconnect between physical simulation and artistic intent, requiring manual intervention in Fusion360. Source reliability is anecdotal, with no evidence of successful final fabrication or measured time savings.
Try it
Act as a creative technical lead for a Burning Man art installation. I need to prototype a Koons-style balloon animal simulator. 1. Use ChatGPT to generate 5 reference images and prompts for a [replaceable: specific animal] balloon sculpture. 2. Use Claude Code to scaffold a [replaceable: language] physics simulation backend and a web frontend that streams geometry. 3. Implement a loop using [replaceable: browser automation tool] to position the camera and capture screenshots for visual review. 4. Export the final geometry to [replaceable: CAD software] for manual refinement. Before generating code, ask me to confirm the [replaceable: animal] topology constraints. After the initial scaffold, run a dry simulation and show me the screenshot output for approval before proceeding to complex twist mechanics. Do not publish or send any files externally without my explicit confirmation.
Source reports are not independently verified. Publication date is the catalog publication date, not the original article date.