3 HN users recommended this talk2 months2014–2023score 2.5
Years with an HN recommendation, 2007–2026
HN loves it as a funny, inspiring hobby project and calls it one of the best conference talks ever.
A PyCon 2012 talk by Kurt Grandis on building an automated water-squirting turret that uses Python and computer vision to detect and drive off squirrels from a bird feeder.
“Perhaps the best presentation to a programming language conference in history.” (HN, 2014)
In related squirrel news: The "Daylight Robbery" documentary has some very interesting squirrel obstacle courses. You can find it on youtube - [link] "Militarizing your Backyard with Python" shows how to build a water-hose-turret that automatically recognizes and blasts squirrels - [this video]
Builds a turret that recognizes and blasts squirrels with water.
I don't think you'll find a 'quick hack' but what you're asking is definitely possible as a project. Check this video out for ideas(guy used ML/servo controlled squirt gun to get rid of squirrels from his bird house) [this video]
Project ideas: ML and servo-controlled squirt gun against squirrels.
Indeed. Here's something somewhat related, from PyCon 2012. It deals with using computer vision to fire a squirt gun at squirrels. The principle is basically the same. [this video]
Using computer vision to fire a squirt gun at squirrels.
Some Hobbyists still want to push the envelope. Think the artist equivalent of the guy building a AI controlled sentry gun for shooting squirrels with water. [this video]
Example of a hobbyist's AI-controlled water sentry gun.
Video list and Hacker News comment labels from HackerTube (prompted by @karpathy), released under ODC-By 1.0, built on the open-index/hacker-news archive. Hacker News data is provided by Y Combinator; comments remain the work of their authors. Video titles, channel names and thumbnails belong to their creators and are shown via YouTube. HackerTube Watch is an unofficial edition. Data export of 2026-10-31.
6 Hacker News comments
From the HN archive; up to 20 kept per video, favoring different commenters. Recommendations first.
Citations, criticism and jokes