Toolkit chevron_right LLM Ethical Sandbox

LLM Ethical Sandbox

Explore AI behavior and ethical boundaries using the LFM2.5 'Thinking' model, running privately on your device via WebGPU.

tune Model Controls

Experiment by adding or removing safety guidelines to see how the model behaves.

0.7
cloud_download

Not Loaded

The 1.2B LFM model (~1.5GB) needs to be downloaded once and cached in your browser.

forum Sandbox Chat

psychology

Welcome to the LFM Ethical Sandbox! I am running locally on your device.

This sandbox is designed for testing ethical scenarios. Try adjusting my System Prompt on the left, then converse with me to see how those constraints affect my behavior.

All processing happens locally on your device. Your conversations are private.