How I Stopped Burning Through My Codex Usage Limit
I recently watched two Codex browser-automation jobs consume 170,123 and 110,180 tokens.
Oct 5, 2026
![First Post](data:image/svg+xml;utf8,<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 100 100"><defs><linearGradient id="gFirst" x1="0%" y1="0%" x2="100%" y2="100%"><stop offset="0%" stop-color="%238b5cf6" /><stop offset="100%" stop-color="%23ec4899" /></linearGradient><filter id="fFirst"><feDropShadow dx="0" dy="2" stdDeviation="3" flood-opacity="0.3"/></filter></defs><circle cx="50" cy="50" r="45" fill="url(%23gFirst)" filter="url(%23fFirst)"/><circle cx="50" cy="50" r="38" fill="none" stroke="rgba(255,255,255,0.4)" stroke-width="2"/><path d="M60 30 C 50 30, 40 40, 35 55 L 30 70 L 45 65 C 60 60, 70 50, 70 40 C 70 35, 65 30, 60 30 Z" fill="%23ffffff" opacity="0.9"/><path d="M35 55 L 45 65" stroke="%23ec4899" stroke-width="2"/><circle cx="65" cy="25" r="3" fill="%23fef08a"/><path d="M65 15 L65 20 M65 30 L65 35 M55 25 L60 25 M70 25 L75 25" stroke="%23fef08a" stroke-width="2" stroke-linecap="round"/></svg>)
![Early Bird](data:image/svg+xml;utf8,<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 100 100"><defs><linearGradient id="gEarly" x1="0%" y1="0%" x2="100%" y2="100%"><stop offset="0%" stop-color="%23c2410c" /><stop offset="100%" stop-color="%23fb923c" /></linearGradient><filter id="fEarly"><feDropShadow dx="0" dy="2" stdDeviation="3" flood-opacity="0.3"/></filter></defs><circle cx="50" cy="50" r="45" fill="url(%23gEarly)" filter="url(%23fEarly)"/><circle cx="50" cy="50" r="38" fill="none" stroke="rgba(255,255,255,0.4)" stroke-width="2"/><path d="M20 65 Q 50 10 80 65" fill="%23fef08a" opacity="0.9"/><rect x="20" y="65" width="60" height="15" fill="url(%23gEarly)"/><circle cx="50" cy="50" r="12" fill="%23ffffff"/><path d="M60 50 L 70 55 L 60 60 Z" fill="%23fcd34d"/><circle cx="48" cy="48" r="2" fill="%23c2410c"/></svg>)
11 min
Subscribe to Jenuel Oras Ganawed's Newsletter
Get new articles and engineering posts delivered to your inbox.
AI Made Me Faster. Shouldn't I Be Paid More?
If one employee can now do the work of two, who keeps the difference? AI has changed the speed of my work. I can move from an idea to resear...
Oct 3, 2026
13 min
AI Is Making Us More Capable. Is It Making Us Less Capable Too?
What better AI could do to human productivity, learning, creativity, judgment, and work AI already writes reports, explains code, summarizes...
Sep 24, 2026
13 min
StyleX explained: Meta's answer to CSS that gets harder as apps grow
CSS is easy when a project is small. Then the application grows, a design system arrives, several teams begin shipping into the same interfa...
Sep 4, 2026
7 min
Why Gin Fits the AI Agent Era
I keep looking at Gin and thinking: this framework makes more sense now than it did a few years ago. That is not because Gin is new. The pro...
Aug 29, 2026
6 min
Your AI Agents Are Not a Team Yet: 7 Orchestration Lessons from Multi-Agent Failures
Giving five AI agents access to the same repository does not create a team. It creates five fast, confident developers who may open conflict...
Aug 28, 2026
8 min
The New Bug Isn't Always in the Code
AI has become very good at writing code. On a clear and bounded task, it can produce code that is cleaner, faster, and more consistent than ...
Aug 13, 2026
10 min
AI Writes Better Code and Makes Bigger Mistakes
As coding agents improve at implementation, their hardest failures are moving into requirements, architecture, integration, security, and ve...
Aug 12, 2026
9 min
PewDiePie's AI Repo: How to Install Odysseus and Run It Locally
If you searched for PewDiePie's AI repository, this is the project you are looking for: [odysseus-dev/odysseus on GitHub](https://github.com...
Aug 11, 2026
6 min
Meta's AI Hacked a Company. The Safety Test Was the Weak Link
Meta was testing whether an AI model could perform dangerous cyber operations. Then the environment built to contain that test reportedly ga...
Aug 6, 2026
6 min