The TUI version of Claude Code just isn't very good, though. The default keybindings do not work in the majority of terminals (because they generate the same byte sequences for key sequences assigned to different commands). Editing large prompts is rather painful because there doesn't seem to be in-prompt search commands. There is no source code browser, so source code references cannot checked by the users without a separate tool. Diffs cannot be copied directly because they are indented by spaces (even though some tools strip indentation from patches, it's still ugly). Switching between conversations is somewhat discouraged by the interface, which makes it harder to keep the context clean.

I think it's possible to have a better TUI, with something that isn't modeled after a shell prompt. Apparently, recent updates move in that direction. The GUI version of Claude Code seems to be coming to Linux, too.

The tide is turning though. I was using the old non agent view in cursor every day for about a year when I built my startup with it. Then Claude Code blew it out of the water. But since two month or so I much prefer Codex and Cursor with the agent view.

However, what I see cooking at Cursor is way more promising than the others. Things like full system understanding, their own forge, multi-repo support. I'd put them as way more visionary in the Gartner magic Quadrant ;)

I saw that happen culturally. But never saw that much different in performance. And I really dislike terminal development. And their desktop app is really buggy.

Claude code is a decent harness but then you have to use Anthropic models, which are good but no longer the best bang for the buck.

In particular Haiku 4.5 is rubbish, Anthropic don’t have anything in the cheap/fast part of the market.

For people fortunate enough to still be on a subscription instead of per-token billing this is less relevant, but their time will come.

The cursor model is quite nice because it allows you to switch between cheap and expensive models for different tasks

Cursor has a surprising amount of inertia, though, at least where I work.

To provide inference, Anthropic and OpenAI need to also constantly spend resources on training new models.

If either one of them stops doing that, customers will stop using them, because other models will become better.

In other words, there is no point in talking about inference cost in isolation.

OpenAI leaked financial data (2025) suggests this - it has $5.7 billion for marketing which 44% of revenue. It’s hard to explain where these billions go other than into subsidised subscription plans and a free tier.

Because using chinese models on OpenRouter is way more expensive than the equivalent codex sub, unless you use something clearly inferior like deepseek flash.

> Inference is cheap;

When they outsource training to China they will be so profitable!

cursor adds $0.25/M to your token bill for 3rd party services. sounds small but it's insanely big on cached inputs, which are an insanely high % of use

If the Opus/Fable harness is superior and it's written using Opus/Fable then it will cease to be a moat. Otherwise the premise for coding using LLMs is essentially untrue.

Couldn't you just download cursor, not even pay for any account and hook up an Anthropic api key and get that functionality?

I dont know how cursor works. Everytime ive tried to use, its super buggy and has memory leaks that make my very quite PC sound like a jet engine.

Codex sub is way cheaper than equally strong models on openrouter.

Surely the days of being able to “bring your own subscription” to a third party platform are also numbered?