2025
LLM post-training with GRPOSeptember 22, 2025
DQN for Atari Breakout from ScratchSeptember 10, 2025
Ideological Bias Auditing in LLMsAugust 7, 2025
Minimal C++ Autograd EngineJanuary 17, 2025
2024
Torchify: Compiling a json-like file to a torch.nn.ModuleOctober 19, 2024
Schokoban: Monte Carlo Tree Search for Solving SokobanAugust 1, 2024