This is your work, valued
AI/ML Research @ Morgan Stanley PhD Cornell University
loophole. Python
410hermitclaw. Python
327DeepSeekRL-Extended. Exploring Applications of GRPO
252picoDeepResearch. Python
692025_advent_of_small_ml. Python
22completion_tree_view. HTML
15nano-grpo-envs. Python
9modded-nanogpt. NanoGPT (124M) quality in 8.2 minutes
4nbn-gpt. Python
3forum_chat. Python
3rainbow_dqn. Python
3popcorn. Local tool for processing a reading list into a biweekly post, with Claude-generated summaries, screenshot OCR for tweets, and per-entry chat. Inspired by Karpathy's LLM Wiki idea.
3base-model-agents. Python
2simple_rlm. Python
2pass-the-turing-test. A reality-TV game show for language models. Six LLM agents each believe they're the only AI in a room of humans. They have to pass for human or get voted off.
2autopcb. The Karpathy ratchet, applied to physical hardware design. Autonomous LLM loop that optimizes PCB component placement.
2nbn-agentic-podcast. Python
1auto-harness. Python
1