[laborcontract]

The reason why OP is getting terrible results is because he's using Cursor, and Cursor is designed to ruthlessly prune context to curtail costs.

Unlike the model providers, Cursor has to pay the retail price for LLM usage. They're fighting an ugly marginal price war. If you're paying more for inference than your competitors, you have to choose to either 1) deliver equal performance as other models at a loss or 2) economize by way of feeding smaller contexts to the model providers.

Cursor is not transparent on how it handles context. From my experience, it's clear that they use aggressive strategies to prune conversations to the extent that it's not uncommon that cursor has to reference the same file multiple times in the same conversation just to know what's going on.

My advice to anyone using Cursor is to just stop wasting your time. The code it generates creates so much debt. I've moved on to Codex and Claude and I couldn't be happier.

[addandsubtract]

What deal is GitHub Copilot getting then? They also offer all SOTA models. Or is the performance of those models also worse there?

[laborcontract]

Github Copilot is likely running models at or close to cost, given that Azure serves all those models. I haven't used Copilot in several months so I can't speak to its performance. My perception back then was that its underperformance relative to peers was because Microsoft was relatively late to the agentic coding game.

[rhim]

> Or is the performance of those models also worse there?

The context and output limit is heavily shrunk down on github copilot[0]. That's the reason why for example Sonnet 4.5 performs noticeably worse under copilot than in claude code.

[0] https://models.dev/?search=sonnet+4.5