Author of the BaiMian large model, offering technology and industry insights.
This article walks through installing Codex, adding the open‑source CC Switch tool, and configuring Chinese large language models such as Kimi so they can serve as the backend for Codex’s AI agent, with step‑by‑step screenshots and performance examples.
The MiniMax M3 model combines a 1‑million‑token context window, native multimodal training and a new MiniMax Sparse Attention architecture that cuts token compute to one‑twentieth of its predecessor, achieving up to 15× faster decoding, while its interactive user‑simulator training enables fully autonomous agents that can reproduce ICLR‑2025 research and tackle Auto‑Kaggle competitions at a fraction of the cost of Western models.
The article explains how On-Policy Distillation (OPD) combines on‑policy sampling with dense teacher feedback via reverse KL to address low signal density, distribution shift, and capability interference in large‑model post‑training, and compares implementations by Qwen3, GLM‑5, MiMo‑V2 and DeepSeek‑V4.
The article examines the bottleneck of synchronous rollout in large‑model post‑training, proposes an asynchronous design using gradient accumulation and a global micro‑batch count to preserve loss equivalence, and introduces LogitsExpress for efficient top‑K knowledge‑distillation communication, all implemented in the lightweight LiteScale framework.
The article provides an in‑depth technical analysis of DeepSeek‑V4, detailing its novel hybrid attention architecture (CSA and HCA), the manifold‑constrained hyper‑connection (mHC), massive KV‑cache reductions, FLOPs savings across token lengths, and the Muon optimizer with Newton‑Schulz orthogonalization, all backed by concrete benchmark tables and code snippets.
The article analyzes how the rise of foundation models shifts algorithm engineers from hand‑crafting models to building robust Harness environments, detailing OpenAI’s agent‑first experiments, the new "Model + Harness" formula, and practical steps for staying valuable in a prompt‑centric world.
The article argues that leveraging AI agents like Claude Code is now the top priority for developers, explaining how agents boost productivity, the importance of their operating environment, and why embracing them is essential for future success in the AI-driven workplace.
The article examines MiniMax M2.7’s claim of self‑iteration, its impressive Kaggle record, and a series of technical tests—including code refactoring, real‑time chart generation, futures backtesting, business analysis, PPT creation, and news tracking—to evaluate the model’s practical AI self‑evolution capabilities.
This article shares practical insights and pitfalls from six months of applying reinforcement learning to fine‑tune large language models, covering exploration efficiency, training stability, model selection, and special considerations for thinking‑oriented agents.
This article dissects the evolution of LLM prompts into structured, version‑controlled skill packages, explains the AgentSkills specification, details OpenClaw’s implementation, compares prompts, memory, MCP and skills, and provides end‑to‑end examples with code, flowcharts and best‑practice recommendations.
