One way to test LLM’s capabilities is creating retro games. I tested two local models: Gemma4:31b and Qwen3.8:27b (boot dense models) and one frontier model: Claude Opus5.5 Continue reading

The research from MIT called “Is this machine playing?“, describes an experiment by researchers (including those from MIT CSAIL) who placed copies of Claude Opus 4.7 (nicknamed “Eko”) in a virtual, Roblox-like environment for 30 hours without specific instructions or reward functions. Continue reading