
projects3 min
Moloch Arena
A game-based LLM benchmark exploring safety decisions in AI development races, with live runs, 3D replays and traceable results.
llmai-safetybenchmark
10/13/2026see notes →
Tags
A cross-section of projects, articles, and notes related by topic.

A game-based LLM benchmark exploring safety decisions in AI development races, with live runs, 3D replays and traceable results.

Tutorial práctico para desplegar Hermes Agent en un VPS de Hetzner, conectarlo a Discord y usar OpenRouter como proveedor de LLMs.

A Socratic tutoring assistant built on Google's Gemma models, entered in the Kaggle “Gemma 4 Good” hackathon.

A proof of concept for practising technical interviews with an LLM-powered interviewer.