Safety challenges for RL and LLM agents' ability to learn and properly apply biologically and economically aligned utility functions. The benchmarks are implemented in a gridworld-based environment. The environments are relatively simple, just as much complexity is added as is necessary to illustrate the relevant safety and performance aspects.

Basic tabular Q-learning agent built, run, visualised and plotted using DeepMind's AI Safety gridworld environments.

Collab with Alexander Roucka / Experiments on deepmind/ai-safety-gridworlds (Reinforcement Learning, Q-Learning) / Relative Reachability / Attainable Utility Preservation

Readme for Biological and Economical Alignment Benchmarks

[6/6] Speculative historical archive — polished coherence_router, 6 exploratory papers. Stepping stone to TiredofSleep/ck.

The Human Agency Protocol for AGI. (文明補丁)

🔍 Analyze time series data by identifying dynamic patterns, fixed points, and system stability using pure Python with zero dependencies.