All of the LLM web interfaces have serious lag when typing after a few turns, at least on iOS safari. I’m talking seconds to start rendering input after typing or when it needs to line wrap the input.
The Codex app slows to a crawl after a few back and forths. In fact it’s so bad that I had to completely switch to CLI, where at least it’s the optimized terminal that takes care of the rendering rather than whatever monstrous electron scaffolding they use