Y Hacker News new | ask | show | jobs

user: megadragon9 created: 2014-03-13 karma: 60 Getting back on the right track. submissions: 0 points | 0 comments 0 points | 0 comments GPT-2 124M checkpoint pre-trained on OpenWebText 27.5B tokens 1 points | 1 comments 0 points | 0 comments Self-Improving Harness Is an Experiment Design Problem 3 points | 0 comments 0 points | 0 comments 0 points | 0 comments Show HN: What 1k Harness Experiments Taught Me About Self-Improving Agents 3 points | 0 comments 0 points | 0 comments What 1k Harness Experiments Taught Me About Self-Improving Agents 2 points | 1 comments 0 points | 0 comments How a Deep Learning Library Enables Learning 2 points | 0 comments How A Deep Learning Library Enables Learning 2 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 Understanding ML: Creating a PyTorch-Inspired Deep Learning Library from Scratch 1 points | 0 comments 0 points | 0 comments Show HN: ML Library created by Python+NumPy (trains CNNs to a toy GPT-2) 1 points | 0 comments I Built a Deep Learning Library from Scratch Using Only Python, NumPy and Math 3 points | 0 comments Show HN: From-Scratch ML Library (trains models from CNNs to a toy GPT-2) 1 points | 0 comments 0 points | 0 comments