QuestLearn: Shadows of the Machine — A Retro Socratic Coding RPG Powered by Open-Weight Gemma

Описание и применение

QuestLearn — браузерная RPG‑платформа, обучающая программированию через интерактивный терминал и диалог с цифровыми духами, использующая открытые модели Google Gemma и изолированные среды выполнения.

Задача

Students learning core computer science principles often rely on closed, cloud‑based grading systems that expose data, impose paywalls, and fail in low‑bandwidth environments.

Результат

QuestLearn demonstrates that open‑weight AI models can deliver real‑time, Socratic tutoring without exposing student code, while sandboxing and offline fallbacks ensure safety and accessibility.

Рабочий процесс

• 1. Learner accesses the web terminal at the provided URL.
• 2. Learner runs "scan" to view a buggy Python subroutine and traceback.
• 3. Learner asks a guided question with "commune <question>" and receives a Socratic prompt from an AI persona.
• 4. Learner writes a patch in the in‑terminal editor and submits it with "patch" or "edit".
• 5. The backend validates the patch via AST inspection, runs it in a 2‑second sandboxed subprocess, and logs results.
• 6. If the test passes, system integrity increases and the next sector unlocks; if it fails, the ancestor adapts hints.
• 7. Upon reaching 100% integrity, the player receives an AetherOS System Integrity & Mastery Exorcism Certificate.

Доказательства

QuestLearn is an interactive, browser-based retro terminal role-playing game (RPG) designed to teach core computer science principles through narrative debugging and Socratic dialogue.

Источник

Powered by open-weight Google Gemma models, the AI core dynamically evaluates runtime errors and adapts puzzle difficulty in real time without ever providing verbatim code solutions.

Источник

The backend validates the patch via AST inspection, runs it in a 2-second sandboxed subprocess, and logs results.

Источник