Thoughts Sol vs. Fable: Stop Asking Which Model Is Best
A grounded way to compare GPT-5.6 Sol and Claude Fable 5 using your own tasks, acceptance criteria, review effort, and cost per accepted change.
7/9/2026
Thoughts
Thoughts
Thoughts posts on The Code Abides.
- Thoughts
-
Thoughts Vibe Coding After Autocomplete: The Agent Is Now the Interface
AI coding has moved from suggesting the next line to operating editors, terminals, browsers, and cloud environments. Here's what that changes.
7/8/2026
-
Thoughts The Metric That Matters: Cost per Solved Coding Task
Token prices are only the beginning. Measure retries, review, cleanup, latency, and accepted changes to understand the real economics of AI coding.
7/4/2026
-
Thoughts The Death of the Junior Dev Myth in 2026
AI didn't kill junior developers; it redefined them. Here's why the 'junior' title means something completely different in the vibecoding era.
2/23/2026
- Thoughts
The Evolution of Cursor: Why Vibecoders Made the Switch in Late 2025
An analysis of how AI-native IDEs like Cursor have dominated the vibecoding scene, becoming the default editor for the new era of developers.
11/20/2025
-
Thoughts The Late-Night Philosophy of Code
A reflection on fatherhood, work, and the quiet power of late night coding. Building toward freedom one project at a time.
10/5/2025
-
Thoughts The Zen of Vibecoding: What It Means to Me
What is vibe coding to me? A personal reflection on AI-assisted coding, creativity, and the joy of turning ideas into real experiences with ChatGPT-5 Codex.
9/21/2025