Y Hacker News new | ask | show | jobs

user: aportnoy created: 2017-08-14 karma: 1277 email: aportnoy@pm.me submissions: 0 points | 0 comments Train an RL agent to play tic-tac-toe 3 points | 1 comments 0 points | 0 comments Show HN: Reinforcement learning tic-tac-toe in C, annotated 2 points | 0 comments Pretraining Large Language Models with NVFP4 1 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments Visualize core-to-core latency 2 points | 0 comments 0 points | 0 comments Show HN: Visualize core-to-core latency in ~200 lines of C and Python 2 points | 1 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments