Running Agents 1 Ready Cohorts Explorer 🚀 1 Explore GPU-ready cohorts for deterministic agent control.
Sleeping Agents 1 FlavourBench 🍲 1 Explore and compare LLM performance on the FlavourBench leaderboard
Running 1 Combining LLMs Rarely Beats the Single Best Model 🎲 1 beta=P(all wrong): the co-failure ceiling on LLM ensembles
Running 1 AEGIS - A Backup Reflex for Physical AI 🛡 1 Interactive companion to the AEGIS backup-reflex paper
Running Agents 1 AURA - A Robot Memory That Never Grows 🟩 1 Live demo of AURA, a robot memory that never grows
Running Agents Featured 63 Epicure Explorer 🌶 63 Operators behind the FlavourBench culinary benchmark