/goal: The Six-Hour Codex Run That Survived a Five-Hour Pause
OpenAI shipped /goal in Codex CLI v0.128.0. Here is what changed in the release, what /goal actually does, and what a real six-hour run looks like.
AI & LLM
LLM Integration, RAG Systems, and AI Enablement.
From SPEC.md to /goal: My Codex + GPT-5.5 Workflow
Two models, one pipeline. How I use Claude for SPEC.md, GPT-5.5 to refine, and Codex /goal to ship long-running work.
My Thoughts on Claude Opus 4.7
Anthropic's Opus 4.7 landed with big benchmark wins, a new tokenizer, and a split reception. Here are the facts, the community pushback, and how I'm using it.
How I Built My First iOS App with AI
I shipped a native SwiftUI app to the App Store with zero prior iOS experience. Here's every tool and workflow that made it possible.
The Interview Method: How AskUserQuestionTool Changed My Claude Code Workflow
Stop prompting. Start interviewing. How a simple tool turned Claude Code into my product co-pilot.
Context Corruption: Why Your AI Agent Forgets What You Told It
The longer a conversation with an LLM runs, the worse the performance gets. How context rot works, why it's unavoidable, and what you can do about it.
The Ralph Wiggum Loop: Running AI Agents for Hours, Not Minutes
How a simple bash loop is changing the way we tackle complex tasks with Claude Code. A paradigm shift for autonomous software development.