Author of the BaiMian large model, offering technology and industry insights.
The article reviews the rapid shift in 2025 from complex workflow‑based LLM orchestration to streamlined agentic systems that rely on simple prompt loops, sandboxed tool execution, file‑based memory, and modular skill files, culminating in the rise of Agent Harness runtimes.
This article reviews the three open‑source Qwen 3.5 models—including a 35B MoE, a 122B MoE, and a 27B dense version—detailing their parameter layouts, core attention designs, context length, inference performance, hardware requirements, and provides step‑by‑step code examples for loading them with Hugging Face Transformers and vLLM.
This article recounts the challenges of moving from single‑step RL with verifiable rewards to multi‑step agentic reinforcement learning in terminal environments, detailing infrastructure design, asynchronous pipelines, data quality checks, masking strategies, curriculum training, chunk‑based optimization, and practical lessons learned from large‑scale experiments.
The article reviews the newly released GLM-5 model, highlighting its ability to generate end‑to‑end system designs, write and debug backend code, and solve large‑scale engineering problems through detailed prompts, positioning it alongside GPT‑5.3 and Claude Opus in the competitive LLM landscape.
The article evaluates Skywork's newly released Windows desktop AI agent by testing it on news aggregation, file organization, PC purchase research with PDF generation, and comparing its features—such as native Windows support, multi‑model auto mode, 100+ built‑in skills, and local VM isolation—to Claude Cowork, while also noting pricing and download details.
This article reviews recent 2025 advances in long‑sequence LLM inference, covering Kimi Linear attention, DuoAttention and DeepSeek Sparse Attention, MegaKernel and MPK designs for kernel‑level efficiency, reinforcement‑learning rollout optimizations, and the Tawa deep‑learning compiler framework.
This comprehensive guide walks through reinforcement learning fundamentals, MDP modeling, value functions, Bellman equations, and key algorithms such as Q‑learning, REINFORCE, PPO, DPO, and GRPO, then contrasts LLM‑RL with Agentic‑RL and surveys leading industry frameworks and real‑world applications.
In this in‑depth interview, Peter Steinberger explains how AI agents let him submit and merge hundreds of commits daily, replace traditional code reviews with prompt‑driven requests, and redesign his development workflow around a closed‑loop validation system that reshapes modern software engineering.
This guide walks you through installing the open‑source Moltbot (formerly Clawdbot), configuring it with the MiniMax M2.1 large‑language model, and connecting it to messaging platforms such as Telegram, WhatsApp, and Feishu, enabling a continuously running AI assistant that can handle emails, code edits, and complex tasks.
This article presents a hands‑on evaluation of Kimi K2.5 and its open‑source Kimi Code agent across a series of hard‑core prompts, covering Python API generation, cost‑optimized routing, multimodal ECharts visualisation, massive‑scale SQL optimisation, web‑search‑driven research, MoE explanation and video‑to‑code workflows.
