What POC demonstrates
- Generation of functional modules.
- Generation of user-interface components.
- Compilation and feedback as part of the evolution loop.
- Operation across macOS, Windows, and Linux.
← Artificial Intelligence
Self-Evolving Software
Project Semilla
An experiment in software that can modify its own source code to introduce new functionality or evolve existing functionality while preserving a working application.
Areas of Work: Artificial Intelligence
Research Question
Can software progressively accumulate capabilities?
Project Semilla moves beyond using AI as an external coding assistant. The intelligence becomes part of the application's own evolution cycle: a requested capability is translated into development tasks, source code is generated or modified, the result is compiled, failures are inspected, corrections are attempted, and successful changes are integrated.
The long-term question is not simply whether AI can generate code. It is whether software can evolve while remaining understandable, controllable, and owned by the person using it.
Evolution Cycle
From request to integrated capability
User requirement→Development tasks→Generate / modify code→Compile→Inspect feedback→Correct→Integrate
Research themes
- Runtime software evolution.
- Source-code modification.
- Automated compilation and validation.
- Iterative self-review.
- Persistent capability accumulation.
- User-controlled software evolution.
Current direction
POC works and can generate functional modules with UI. Current development work includes path handling, broader testing, refinement of the main GUI, review of GitHub integration, and stronger user control over the evolution process.