Y Hacker News new | ask | show | jobs

user: desideratum created: 2019-07-24 karma: 221 submissions: 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments Nanocode: The best Claude Code that $200 can buy in pure JAX on TPUs 219 points | 26 comments Batrachochytrium Dendrobatidis 4 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments Finetuning GPT-OSS with Axolotl 3 points | 0 comments Accelerate ND-Parallel: A Guide to Efficient Multi-GPU Training 3 points | 0 comments Training LLMs with GRPO and Interpreter Feedback Using WebAssembly 3 points | 0 comments Training Large Language Models with Interpreter Feedback Using WebAssembly 1 points | 0 comments DeepSeek-V3-0324 5 points | 1 comments Training Process Reward Models in Axolotl 2 points | 0 comments 0 points | 0 comments 0 points | 0 comments Torchtune – a native PyTorch library for fine-tuning LLMs 2 points | 0 comments 0 points | 0 comments (Deep Learning Based) Opportunistic Screening to Improve Statin Rates 1 points | 0 comments The theory of Proximal Policy Optimisation implementations 1 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments