China just put claude opus behind on two AI agent tests
On August 21, DeepSeek quietly released V4-Flash-Vision-Exp, an experimental multimodal model. In DeepSeek’s own published table, it scored higher than Claude Opus 4.8 on Agents’ Last Exam, 27.3 vs 25.7, and ZeroBench
DeepSeek V4 Flash Vision Exp on opencode has all my cameras.
Full gimbal control OBSBOT_Official and my S25+ in opencode.
[OpenSource - Large MoE Inference & Local AI]
Running massive 671B parameter Mixture-of-Experts (MoE) models like DeepSeek-V3 or DeepSeek-R1 usually requires enterprise server clusters costing tens of thousands of dollars. 🛑 ktransformers by Tsinghua University / kvcache-ai is
Holy shit this is a f**king gold
I replaced opus 5 with deepseek harness, it's basically free it is built around one core idea: everything is a plugin [it takes 3 mins to set up here is how] 1. install this repo called 'deepseek-harness' 2. read the architecture docs 3.
You have reached the end of the archive
All of deepseek