Anyone else observing a massive gap in LLM capabilities within Cursor? For example, ChatGPT 5.2 is 1000x better when used in chatgpt.com than when used inside Cursor. It’s gotten so bad that I am now copying and pasting things from Cursor GPT5.2 into ChatGPT 5.2 to fix all the problems the Cursor L…

Hey, thanks for the feedback. Cursor uses the same exact models directly via the OpenAI and Anthropic APIs, so these aren’t separate “cut down” versions. The model call settings are standard too. The main difference is usually that Cursor adds extra context: Code from your project Rules for AI S…

I recommend MAX mode. Without it the 250 line limit can severely affect the output – you’ll notice the same issue with copilot

[image] RawToast: Without it the 250 line limit can severely affect the output Agent in Cursor can write over a thousand lines at a time. What limit are you talking about?

what about Ask modes and Plan modes? Because at this point, I am getting much better results using GPT 5.2 in ChatGPT.com to build plans rather than calling the same LLM in plan mode

I hate to corroborate the experience of the OP, however, there does appear to be something about Cursor, that seems to make the models…..well, dumber, than their “raw” counterparts. I had to use Claude Code alongside Cursor recently, because I was updated to 2.4.x, and it was a disaster. First the …

in theory the main difference is the system prompt that Cursor AI adds. Same goes for Claude Code It is possible Cursor AI team keeps meddling with system prompts. There may be a lot of junk that confuses the model

That is my suspicion as well, but I have little to back it up, its just a suspicion. I have a fair amount of rules, however I recently (just a couple days ago) went through and marked most of them as “Apply Manually”, reducing the baseline rule load to about 6-9. It varies depending on some “Apply I…

Here is an exemplar case right here. This used to work PERFECTLY! My rule is VERY clear about how the agent should run httpie. Despite the rule being apply intelligently with all the necessary description details to have it apply whenever the agent tests, I still explicitly reference it as well beca…

It’s input not output. The file_read tool is limited to 250 lines per call. Some models may call it multiple times to get more input So if you give it a 600 line file, it may only read 250 lines; although, it could make another call for 500, or two for all 600. Max can read up to 750 in one tool ca…

[image] RawToast: The file_read tool is limited to 250 lines per call Gemini 3 Flash: [2026-01-28_11-48-39] [image] RawToast: So if you give it a 600 line file, it may only read 250 lines; although, it could make another call for 500, or two for all 600. Max can read up to 750 in one …

Cursor LLMs Lobotomized?

Discussions

RawToast (RawToast) January 28, 2026, 1:56pm 13

If they’ve changed this, they need to make it clear:

@condor

Topic		Replies	Views
Why does Cursor produce richer/more accurate outputs than Claude Code with the same Opus 4.6 Extended Thinking model? Discussions context , anthropic	1	540	February 15, 2026
Insane Laziness In Agent Feedback	31	1065	September 24, 2025
Opus Max (500usd) No Fix vs GPT o3 Fixed in 3 msgs Discussions	30	1362	July 26, 2025
GPT-5 paralyzed by excessive thinking? Discussions	8	832	September 17, 2025
People, Your Honest Opinion Discussions	23	2844	March 18, 2025

Cursor LLMs Lobotomized?

Related topics