AI practitioner specializing in large-model evaluation and on-premise deployment, agents, AI programming, Vibe Coding, general AI, and broader tech trends, with daily original technical articles.
The article reviews the developer preview of DeepSeek Harness's official desktop client, highlighting its plugin-based architecture powered by Cordis, deep integration with DeepSeek V4.1 Flash model achieving 99% cache hit rate, and comparative performance against other harness integrations like Pi Agent.
DeepSeek-V4.1-Flash open-sourced with CED architecture and 8B/16B activated parameters outperforms its 1.6T predecessor V4-Pro on coding benchmarks, approaches GPT-6 Astra on DeepSWE, but requires 510GB FP8 weights needing 8×H200 for full-context local deployment; author tests across six harnesses finding Claude Code/Codex integration near peak performance.
The author reviews GPT-6 Astra's computer-use capability for Blender 3D modeling, Image 2.5's sketch-to-image and template features, ChatGPT's computer history and skill recording via demonstration, and shares quota-management tips for ChatGPT Pro users.
The article demonstrates how WorkBuddy connects with Feishu via connectors and skills, enabling AI-driven cross-ecosystem workflows like automated accounting, document retrieval, PPT generation, and group chat bots, eliminating manual data transfer between Tencent and ByteDance tools.
After two weeks of intensive use and watching official livestreams, the author reveals five advanced Doubao Work workflows: data-first PPT creation, browser automation for tedious data collection, serverless shareable app building, custom skill development, and candid product feedback for this AI productivity agent.
Analysis of China's AI short drama oversupply (220k+ titles, 0.47% hit rate), new regulations mandating quality, and ByteDance's Xiao Yunque platform solving workflow, incentives, reusable skills, and talent gaps to convert viral hits into lasting IP franchises.
The author evaluates Google's Gemini 3.8 Flash model through hands-on coding, creative, and reasoning tests, finding it excels on benchmarks and cost-efficiency but falls short in agent capabilities, context retention, and practical tasks compared to rivals like Doubao and DeepSeek, while criticizing Google's product management and subscription value.
The author evaluates Doubao-Seed-Evolving's latest upgrades across coding, agent, multimodal, and long-horizon skill execution using real-world tasks like PPT-to-website conversion, personal project management, SVG generation, 3D Rubik's cube animation, and a complex 30-minute web scraping skill, finding strong autonomous task decomposition, testing, and error recovery.
A longtime Lovart user details how the tool's latest upgrade addresses core design workflow pain points with a Chrome inspiration plugin, reusable Skills for consistent outputs, multi-format generation from single ideas, and one-click vector conversion for professional handoff.
ChatGPT's new Computer History feature on macOS captures clicks, keystrokes, and app switches via Accessibility API, builds a searchable timeline, summarizes activity into local markdown memories, and suggests automations for repetitive tasks—available only to Pro, Business, and Enterprise users with granular privacy controls and notable prompt-injection risks.
