An individual experimented with using AI models to develop a custom watch face for a PineTime smartwatch. The PineTime is an open-source, low-cost device, making it suitable for such hacking projects. The inspiration came from observing others using AI for ESP32 device development.
While initially referring to Claude, the developer primarily used OpenCode with open-weight models such as Kimi K3, K2.6, DeepSeek v4 Pro, and DeepSeek Flash. The process began by asking the AI to build the InfiniSim repository on Ubuntu, which was completed quickly.
The developer provided the AI with an image of a desired watch face and an existing InfiniTime watch face code as a starting point. The AI was instructed to replicate the design and orchestrate sub-agents for specific development tasks. The AI produced a rough approximation of the watch face, though it had issues with text sizing and positioning.
The initial AI output required manual intervention for refinement. The developer provided specific feedback and isolated tasks to correct elements like text placement and sizing. This iterative approach was chosen to conserve computational resources and tokens, indicating that while AI can provide a starting point, human oversight remains crucial for achieving pixel-perfect results in such projects.
✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →
One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.
One email a day. Unsubscribe in one click, any time.
Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.
▶ Play today's briefNew every morning, and the back catalogue is archived by date.
An individual used AI models, including Claude and open-weight models like Kimi K3 and DeepSeek v4 Pro, to generate code for a custom watch face on a $27 PineTime smartwatch. This demonstrates the potential of AI agents in assisting with embedded device development, even if initial outputs require refinement.