cognitiveailab/BYTESIZED32

Byte-sized text games for code generation tasks on virtual environments

22
/ 100
Experimental

This project helps AI researchers evaluate how well large language models can generate executable code for interactive text-based virtual environments. It takes descriptions of desired game elements (like objects, actions, and distractions) as input and outputs Python code for text games, alongside detailed evaluation metrics. Researchers focused on code generation, virtual environments, or AI agent training would use this to benchmark and refine their language models.

No commits in the last 6 months.

Use this if you are an AI researcher looking to systematically test and evaluate large language models' ability to generate functional and coherent code for text-based virtual environments.

Not ideal if you are a game developer looking to create interactive text games for human players, or if you need a tool for general-purpose code generation outside of text game environments.

AI-benchmarking LLM-evaluation code-generation virtual-environments AI-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

20

Forks

Language

Python

License

Apache-2.0

Category

ai-powered-games

Last pushed

Jul 08, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/cognitiveailab/BYTESIZED32"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.