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.
SkillOS reframes skill management for LLM agents as a long‑horizon reinforcement‑learning problem, letting a trainable Skill Curator automatically insert, update, or delete markdown‑based skills, which the frozen Agent Executor then consumes, improving memory‑free performance and cross‑task transfer.
The author evaluates Alibaba’s newly released Qwen 3.7‑Max across seven rigorous tasks—including reading comprehension, HTML fireworks generation, 3D particle visualizations, PDF‑to‑PPT conversion, Excel data analysis, GitHub trending scraping, and complex video generation—showing it often surpasses GPT‑5.5‑level models and rivals Claude 4.7, especially in long‑duration agent tasks.
The article examines Volcano Engine’s new Agent Plan, detailing how its bundled flagship models, Seedance image and video generation skills, web‑search and memory capabilities streamline tasks such as browser‑plugin replication, data‑analysis report creation, full‑stack web dashboards, PDF translation, PPT generation, and Three.js visualizations within Claude Code and Hermes Agent, while comparing it to the earlier Coding Plan model.
The author walks through a hands‑on test of the Skywork cloud AI Agent, showing how it can ingest exported Excel data, generate a data‑analysis report, automatically create a PPT, produce narrated video and images, all via a single input without any local deployment.
Google's Gemini Intelligence upgrades Android from an operating system to an AI-driven platform, enabling cross‑app automation, Chrome‑based browsing tasks, intelligent autofill, spoken‑to‑text messaging, and natural‑language widget creation, while reshaping hardware strategy and developer interfaces.
The DeepSeek V4 Flash quantized GGUF model and the dedicated ds4 inference engine, both released by antirez, offer dramatically reduced activation parameters, massive 1‑million‑token context windows, aggressive KV‑cache compression and hardware‑specific quantizations that enable smooth local inference on high‑memory Macs and CUDA machines, while sacrificing generality for performance.
The May 15 open‑source release of X’s For‑You recommendation system reveals a full pipeline—from query hydration and candidate sourcing to multi‑stage scoring—showing that the platform predicts a range of user actions, emphasizes content‑level signals, and offers creators concrete guidance to improve visibility.
The vLLM 0.21.0 release brings five major updates—including Transformers v4 deprecation, a C++20 build requirement, KV offload with hybrid memory, speculative decoding that respects thinking budgets, and a Blackwell token‑speed backend—while offering detailed upgrade guidance for different user groups.
BenchLoop is a CLI‑plus‑Web application that lets you reproducibly benchmark locally‑run LLMs across seven suites—including speed, tool‑calling, coding and agent tasks—while recording hardware details, scoring results with a weighted formula, and optionally publishing them to a public leaderboard.
Qoder 1.0 upgrades from a 0.x prototype to a full‑featured AI IDE with a new independent Quest view, multi‑agent parallelism, end‑to‑end delivery, long‑term memory, extensible expert teams, and full‑stack quality checks, demonstrated by recreating a browser extension in minutes.
