Y Hacker News new | ask | show | jobs

user: helloericsf created: 2022-05-09 karma: 676 submissions: 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments Context Engineering for AI Agents: Lessons 120 points | 4 comments Context Engineering for AI Agents: Lessons 3 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments Better than DeepSeek R1? MiniMax-M1:open-weight hybrid-attention reasoning model 6 points | 0 comments kit - Code Intelligence Toolkit 1 points | 0 comments 0 points | 0 comments DeepSeek Open Source Optimized Parallelism Strategies, 3 repos 103 points | 8 comments 0 points | 0 comments DeepSeek Open Source DeepGEMM – FP8 GEMM Library(300 lines for 1350+ FP8 TFLOPS) 4 points | 1 comments 0 points | 0 comments Alibaba Open Source Large-Scale Video Generative Models: Wan2.1 8 points | 2 comments 0 points | 0 comments 0 points | 0 comments DeepSeek open source DeepEP – library for MoE training and Inference 536 points | 71 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments DeepSeek Open Source FlashMLA – MLA Decoding Kernel for Hopper GPUs 441 points | 108 comments 0 points | 0 comments New Qwen2.5-Max Outperforms DeepSeek V3 in Benchmarks 3 points | 2 comments 0 points | 0 comments Longest context up to 4M, MiniMax-01 hybrid 456B Open source model 19 points | 1 comments