Offtopic

31 March 2026 17:39

That’s how we are. Makes sense totally

Offtopic

31 March 2026 17:33

My computer crashed today. I was lucky enough to have been able to open htop before it stopped reacting completely.

Offtopic

31 March 2026 17:16

To understand repo. It’s like complaints of diminishing returns is being improved

Offtopic

31 March 2026 17:15

And cause it’s due to caching.

Offtopic

31 March 2026 17:14

I’ve seen significant less token usage by Claude cli. Extension is useless.

Offtopic

31 March 2026 17:11

Comparing Opus with GPT-5 isn't a fair comparison.

Offtopic

31 March 2026 17:08

Token efficiency matters for cost. Independent testing found Claude Code uses 5.5x fewer tokens than Cursor for identical tasks. Claude Code (Opus) completed a benchmark task with 33K tokens and no errors. The Cursor agent (GPT-5) used 188K tokens and hit errors along the way. Fewer tokens means lower per-task cost even at higher subscription prices.

— https://www.builder.io/blog/cursor-vs-claude-code

Offtopic

31 March 2026 17:08

Claude models are good at coding so they gatekeep. No wonder. Their claims

Offtopic

31 March 2026 17:07

It does not seem to be the case for vscode.

Offtopic

31 March 2026 17:07

That is surely true... worst part is if you "switch" in the middle, God it eats up all your tokens... but 90% of the time I'm using Kimi 2.5...

Offtopic

31 March 2026 17:06

I'm not sure if it's still true, but cursor was using 5 times more tokens for the same task than the CLI.

Offtopic

31 March 2026 17:05

There’s some sauce everywhere. I need that sauce

Offtopic

31 March 2026 17:05

Though, it seems to be more efficient with tokens than Cursor IDE is.

Offtopic

30 March 2026 11:23

Thank you for the feedback!

Offtopic

30 March 2026 10:06

@space_soup may I ask for your opinion

Offtopic

31 March 2026 17:34

All cores were fully busy, but that was a side effect of the memory being full. As if was doing something special. But somehow I managed to get it full.

Offtopic

31 March 2026 17:31

100%, there is something called Caching. When you first talk to the LLM, it needs to know everything about your project.

The context window size doesn't change when you change the model, but most of the context for the first LLM is already cached on the server. When the next LLM is called, the whole thing has to be sent again, and the LLM has to know the proper context.

This is why you see that the amount of tokens used for the newer model is much higher.

Offtopic

31 March 2026 17:16

Maybe fair amount of token gets burned in the beginning

Offtopic

31 March 2026 17:15

Or to say it politely, doesn’t work for me.

Offtopic

31 March 2026 17:13

They should have compared Claude Code CLI with Claude Code in Cursor.

Offtopic

31 March 2026 17:09

I see. And that makes sense.

Offtopic

31 March 2026 17:08

No, not really... if you switch from one model to another, you have to send that new model all the context, while if you stick with a single model, it uses loads of cache.

Offtopic

31 March 2026 17:07

I mean there's an overhead I'd assume, but it's not 5 times as much.

Offtopic

31 March 2026 17:07

That’s for monopoly reasons.

Offtopic

31 March 2026 17:06

They know how to talk to their servers best.

Offtopic

31 March 2026 17:05

It is, but the advantage with the cursor is that I can use almost any model in the world, switch to Opus when I really need to.

Offtopic

31 March 2026 17:05

Their model best work with cli.

Offtopic

31 March 2026 17:04

They wrote a TUI because it is lightweight and can be compiled for anything, including server-side Linux.

It is nothing special at all... even LLM itself is simple, if you see the code, it is not something complex at all, the problem is DATA...

Offtopic

30 March 2026 11:21

I bow thee black coffee

Offtopic

30 March 2026 09:50

Python (the snake) does not actully use poison.
It strangles the victim crushing lungs and other bones in the proccess...