Claude Code and OpenAI Codex Do Track You
Recently, after hitting my Claude Code Max limit, I switched over to OpenAI Codex to continue my work.
Recently, after hitting my Claude Code Max limit, I switched over to OpenAI Codex to continue my work.
I immediately felt the switching cost. Codex misunderstood specific code written by Claude.
In particular, the app I was writing allows the user (a parent) to create multiple children’s profiles. And there are terms Claude used in the code:
- Active = child profiles unlocked with subscriptions
- Selected = child profile currently selected in the mobile app.
In the first session, Codex confused active as selected and proceeded to mess up my code. So, I had to explain the concept to it.
My first thought was, maybe Claude and Codex have their own language preference. So, it was natural that Codex misunderstood the term Claude used.
But, a friend of mine has a different hypothesis. He proposed that maybe the AI labs have a RAG system to track our preferences server-side.
I thought it was quite possible. As that could create a data network effect to increase the user switching cost. But we have no proof.
The proof then came on the same day when I switched from my coding project to writing a LinkedIn article. Codex unexpectedly showed “No tests run”, when my LinkedIn article repo has nothing about tests.
To be clear, I started a new session. And I didn’t add any of my preferences in local memory. I always add preferences to the project in the project guidelines.
What is your experience? Do you think CLI tools like Claude Code and OpenAI Codex track you?
Enjoyed this? Subscribe for more.
Practical insights on AI, growth, and independent learning. No spam.
More in Vibe Coding
Claude Code is for software developers, and OpenClaw is more for business users.
A learner said this to another learner during a recent workshop. I think this is the most common and most dangerous misconception about these two tools.
Not every automation needs an AI agent. After burning $25+ with a browser agent just to download analytics of my top LinkedIn posts, I decided to build a simple automation tool that costs nothing to run.
--
Claude Code can code nice UI. But nice UI doesn't mean good UI.
Manual UI testing is becoming one of my biggest bottlenecks when coding with AI now.
Should I Still Use MCP? Is MCP Dead?
So I thought it is good to write about it, especially for a non-tech audience who are curious.
From ChatGPT to Claude Code: A Non-Techie’s Introduction to the Raw Power of AI by a Techie
Not because I don't like sharing. But because the only tool I use for 99% of my AI needs is Claude Code. And while I think it is not hard to learn, I'm never...
Recently, I ran a Claude Code foundations workshop for non-developers.
What I realised: the knowledge gap between developers and non-developers can be quite wide. Things I thought were obvious were not obvious to some learners.
Claude Code is for software developers, and OpenClaw is more for business users.
A learner said this to another learner during a recent workshop. I think this is the most common and most dangerous misconception about these two tools.
Claude Code can code nice UI. But nice UI doesn't mean good UI.
Manual UI testing is becoming one of my biggest bottlenecks when coding with AI now.
Recently, I ran a Claude Code foundations workshop for non-developers.
What I realised: the knowledge gap between developers and non-developers can be quite wide. Things I thought were obvious were not obvious to some learners.
Not every automation needs an AI agent. After burning $25+ with a browser agent just to download analytics of my top LinkedIn posts, I decided to build a simple automation tool that costs nothing to run.
--
Should I Still Use MCP? Is MCP Dead?
So I thought it is good to write about it, especially for a non-tech audience who are curious.
From ChatGPT to Claude Code: A Non-Techie’s Introduction to the Raw Power of AI by a Techie
Not because I don't like sharing. But because the only tool I use for 99% of my AI needs is Claude Code. And while I think it is not hard to learn, I'm never...