Who it is forA developer or hobbyist with a PC who wants to see how a small on-device language model picks fish behavior before buying hardware.
The problemReading about a 14M-parameter model on a microcontroller is hard to picture without seeing the decisions happen.
The outcomeA running tank on your PC where each fish's state line is answered with a goal and urgency, and you can see fish hesitate when the model is unsure.
What you need first
- A PC to read the code and run the simulator (the README points to a PC simulator section)
- A C compiler on your PC for the simulator build (inferred)
- A supported Waveshare board for real hardware: 1.8-inch, pendant, watch, or square (the board costs about $35 per the README)
- A USB cable for the first install; later updates come over Wi-Fi from v0.3
Steps
- Clone the repo:
git clone https://github.com/mediacutlet/pocket-tank(inferred) (inferred, check the README) - Open the README section 'Try it: PC simulator' and follow its build steps
- Start the simulator and tap a fish to open its stats card
- Compare the state line in the README with what the simulator shows for the same fish
- Watch for a fish that pauses before committing and note the urgency it reports
Prompt for your agent
Use the mediacutlet/pocket-tank repo on GitHub. Follow the 'Try it: PC simulator' section to build and run the simulator on this machine, then report the goal and urgency the model assigns to the first fish you see. Verify that the simulator runs without error and that a state line appears for at least one fish.
Caveat. The README shows the simulator as a section but the exact build commands are not in the excerpt, so you must read that section before running anything.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page