shipped / October 20, 2026
The Duck Pond: Claude tuned a duck synthesizer in a loop until a classifier rated it more duck than the real duck
score recordings used: 0
celphase, a Rust developer who says audio is outside their wheelhouse, shipped a pond of synthetic mallards. No recordings. Every quack, rhaeb and duckling peep is modelled from the duck's syrinx and vocal tract and placed in space from where you stand on the bank. The build was Claude in a loop, nudging synth parameters until the spectrogram matched a real recording. Along the way a bird-sound classifier rated the fake duck as more duck than the real one. Press p to throw peas.
Built by celphase with Claude.
see the announcement on Hacker News →instructionsdemosource
What it is
The Duck Pond is a web page that sounds like a pond. Three hens called Mabel, Clover and Hazel, a drake called Rufus who stays a little behind his mate, a lone drake called Bramble, and two broods of ducklings. They feed, rest, preen and drift about in bouts that last minutes, roughly 40% feeding and 30% resting. A duckling that strays more than four metres from its mother peeps until she calls it back with soft kwek-kweks, about 3.7 a second. A hen's call can set off the ducks nearby, and her mate is the most likely to answer. Press p, or tap Throw peas, and the nearest ducks race over to eat.
None of it is recorded. "This actually uses no recordings," celphase told one commenter who assumed a sample pack. Every sound is synthesised the moment it happens. Quacks and the drake's raspy rhaeb come from a source-filter model of the syrinx and vocal tract: a train of air pulses, one per vibration, shaped by formant filters that follow the bill as it opens and closes, with jitter, shimmer and period doubling for the rasp. The classic decrescendo is five to seven quacks that get shorter, quieter and lower. Peeps, bubbles, splashes and bill clacks use simpler models. Then each sound is placed by distance and bearing from where you stand on the bank, at 343 metres a second, with air absorption dulling the far ducks, a shared reverb and a low water bed underneath. Headphone mode adds a spherical head model.
The core is Rust with a native player. The browser version is the same code compiled to WebAssembly, rendering in a Web Worker about 170 ms ahead and playing through an AudioWorklet.
How it was built
The repo went up on October 17, the day of the Show HN. The GitHub account's other projects are an OpenXR library, game engine tooling and an 8-bit CPU in Scala, which is not where you expect a duck to come from. When a commenter guessed the thing was LLM-generated, celphase did not argue: "The project was created with significant LLM use, I'd add claude as a co-contributor if I could do so manually." And: "Audio is entirely outside my wheelhouse beyond what happens at the platform API level."
The method: "running the LLM in a loop to gradually correct parameters of a synthesis stack to have the spectrogram of the output match the spectrogram of a real recorded sample." ATTRIBUTION.md names the samples, two mallard recordings from Naturesongs.com used to measure pitch, formants, length and timing, and the judge, the PANNs CNN14 audio classifier trained on AudioSet, used to check that the synthetic calls register as "Duck" and "Quack". The recordings and the classifier were only part of the Python prototyping and are not in the repo. The duck behaviour comes from a reading list of papers on brood calls, time budgets and duckling swim speeds, some of them read only as abstracts, which the file also admits.
"One funny part," celphase wrote, "is where the synthesis was marked by a classification model as more duck than the real duck sample."
Why we picked it
Because the loop was: generate a duck, compare the spectrogram, adjust, repeat, and the human's listed contribution is "a few technical choices." Because the judge was a neural network and it preferred the fake. And because the whole thing is MIT, has a peas button, and is the most relaxing tab you will open today. Free-range tokens. No added samples.
Shipped is Accept All's daily pick of things people build with AI, written by MK. We are not affiliated with celphase; the work and the credit are theirs, so go tell them it's good. Newer: Permit Pending: SimCity, but every bus lane goes through hearings, lawsuits and appeals, and there is no win screen. Older: Five Hundred Clocks: Opus 5.5 ran its own subagents for 18 hours and built 500 clocks into one HTML file.