Tutorials and reviews for developers
Written since 2017, and corrected when the facts change.
A developer's notebook, kept in public
- Since 2017
- Tutorials from real projects: servers, PHP, databases and web scraping.
- Since 2026
- Reviews of AI models and coding tools, each fact linked to its source.
curl -fsSL https://claude.ai/install.sh | bashGLM-5.3-Flash Review: Z.ai’s Open Model That Approaches Claude Opus 4.8 on Agentic Coding at a Fraction of the Price
Z.ai released GLM-5.3-Flash, a 320B MoE model with native vision, 1M context, and MIT-licensed weights that Z.ai says approaches Claude Opus 4.8 on coding and agentic benchmarks at about a tenth of GLM-5.2’s price. Here’s what it costs and whether self-hosting makes sense.
- Z.ai’s New “Ox Alpha” Mystery Model Is Real, Open, and Stupidly Cheap
- What GLM-5.3-Flash Actually Is
- The Ox Alpha Backstory
- Benchmarks: What Z.ai Reports
- Pricing That Changes the Math
- Native Vision, Aimed at the Coding Loop
Every post, by year
2026
- GLM-5.3-Flash Review: Z.ai’s Open Model That Approaches Claude Opus 4.8 on Agentic Coding at a Fraction of the Price
- Alibaba’s Qwen3.8-Max: A 2.4 Trillion Parameter MoE Model That Actually Keeps Up
- Kimi K3: Moonshot AI’s 2.8T Open Model Is Here
- DeepSeek V4 Is Here: 1.6 Trillion Parameters, 1M Context, and Open Weights
- ChatGPT Images 2.0: The AI Image Generator That Finally Gets Text Right
- Docker Compose: Build a Full-Stack Application from Scratch
- Getting Started with Claude Code: The AI Coding Agent That Lives in Your Terminal
New posts, in your feed reader
/* no newsletter, no tracking cookies, just RSS */
https://howpcrules.com/rss.xml Open the RSS feed