Managing Codex-Spark: 1000 Tokens Per Second Changes Everything
I spent a week with GPT-5.3-Codex-Spark on Cerebras hardware. The speed broke every workflow I had.
Insights on software development, AI, and technology.
I spent a week with GPT-5.3-Codex-Spark on Cerebras hardware. The speed broke every workflow I had.
I ran a privacy preserving analysis on 809 conversations. The results were humbling, surprising, and exactly what I needed to see.
What happens when you fine-tune a 14B parameter model on your own coding conversations? Real numbers, real costs, and real frustrations.
My journey from spending thousands monthly on AI subscriptions to building a custom 8x 3090 AI rig for local inference
Months of optimizing my workflow with Cursor and Claude Code. The techniques that actually multiply productivity.