Confidence is not correctness
The dangerous thing about a language model isn't that it's wrong — it's that it's wrong with total fluency. A short case for keeping your judgment in the loop.
oran.chat blog
Essays
Where we stand on agency, model choice, and thinking with AI.
Is Google search dying? What the 2026 numbers say
ChatGPT hit 900M weekly users and ~17% of global queries. Google still sends 190× more traffic. A clear-eyed read of whether search is actually dying.
Keep a model you don't agree with
GPT leads with the consensus; Claude more often surfaces the counterargument. Why the point of using more than one model is disagreement, not redundancy.
Vibe coding and the limits of describing what you want
Vibe coding became a $4.7B habit in 2026 — yet developer trust in AI code fell to 29%. What the gap between describing and knowing really costs.
The case against the all-in-one AI assistant
Why bundling chat, voice, image-gen, browsing, and agents into one product makes each one worse — and what to use instead.
The forgotten skill: knowing when not to ask AI
Some questions are worse for having been asked of an AI at all. A short list of categories where the human answer beats the model answer reliably.
Why one chat with many models beats many chats with one
An argument for the multi-model conversation as the default — what changes when the model picker is per-message instead of per-app.
A quieter place to think with AI
The case for AI tools that get out of your way — what changes when the surface is calm enough that the work, not the interface, is what you notice.
Why "the right model" matters more than "the best model"
The 'which AI is best?' question has the wrong shape. Better question: which one is right for the thing in front of you right now.
The thinking is yours, the models do the typing
A short argument for why agency, not raw output, is the thing AI tools should be protecting. And what that means for the tools you choose.
Where AI tools rob you of agency (and how to take it back)
Four specific patterns by which AI tools quietly take over the parts of your work that should stay yours — and how to notice when it's happening.
What I learned writing with three AI models for a year
Twelve months, three flagship models, one personal essay practice — the patterns that held up across model versions and the ones that didn't.