skip to content- 2026-07-02
|
Pi Coding Agent: Minimal, Programmable Terminal Harness
Set up Pi as a minimal coding harness with GLM-5.2, persistent sessions, compaction, custom tools, extensions, and clear Z.AI policy caveats.
- 2026-07-02
|
Pi vs ZCode vs OpenCode: Which Harness Fits GLM-5.2?
Compare Pi, ZCode, and OpenCode as coding harnesses for GLM-5.2: workflow, permissions, context, setup, quota paths, and a fair same-model test.
- 2026-07-02
|
ZCode: GLM-5.2-Native Coding Harness Guide
Use ZCode as Z.AI's integrated GLM-5.2 coding harness: desktop setup, Goal Mode, subagents, safety confirmations, quota, and workflow trade-offs.
- 2026-07-02
|
How to Read AI Benchmarks Without Getting Fooled
Learn how to read AI benchmarks, spot saturation and contamination, compare coding and chat leaderboards, and test models on your own work.
- 2026-02-17
|
UltraThink → UltraQuiet: Why Devs Want Receipts
Claude Code started hiding file paths and search details behind Ctrl+O. Here's a working fix: the AGENTS.md Audit Ledger pattern.
- 2026-02-11
|
The 20-Minute Blog, Three Years Later: What Actually Works in 2026
On April 4, 2023 I tested GPT-4 blog writing in 20 minutes. This is the 2026 workflow that replaced speed-first publishing: vibe, verify, ship.
- 2026-02-11
|
The Lost AI Posts of April 2023: What Survived, What Failed, What to Publish Instead
A practical reconstruction of three deleted April 2023 AI posts, with 2026 guidance for replacing hype with durable, verified content.
- 2026-02-11
|
Vibe Coding Archive Evidence: 2023 Legacy URLs and 2026 Replacements
Wayback verification log for AIHackers legacy April 2023 post URLs and archived snapshots of their 2026 replacement pages.
- 2026-02-11
|
Vibe Coding Lessons (2023-2026): A Production Playbook
What changed from speed-first AI drafting in 2023 to verification-first publishing in 2026, with a practical playbook for durable authority.
- 2026-02-07
|
AGENTS.md: One File That Makes Agents Behave
A practical guide to AGENTS.md and CLAUDE.md—why they work, how to write them, and copy-paste templates for Markdown projects, Python, and TypeScript.
- 2026-02-07
|
AGENTS.md: What Actually Works (And What Doesn't)
Evidence-based guide to writing AGENTS.md files that AI agents actually follow. Lessons from Vercel's evals, multi-tool testing, and production usage across Python, TypeScript, and documentation projects.
- 2026-02-03
|
Codex vs Claude Code vs Cursor
Current workflow comparison for Codex, Claude Code, and Cursor, with model availability and benchmark claims separated from tool features.
- 2026-02-01
|
OpenCode: Providers, Zen, Permissions, and GLM-5.2
Current OpenCode guide for its open-source coding agent, optional Zen gateway, BYO providers, permissions, integrations, and three GLM-5.2 billing paths.
- 2026-01-23
|
AI Research: What It Gets Right and Wrong
What AI does well, what it gets wrong, and a safe workflow for research.