[flagged]
Cursor removed cost information from the usage page and CSV export
131–140 of 172 posts
Re: Cursor removed cost information from the usage page and CSV export
#132Earlier quoted context omitted.
> Do not underestimate how much popular harnesses are spamming the context window. The context window is very important. Do we have any insight into whether it is actually spam and not useful info such as project or programming language specific context?
in my book anything that is (I'm sure well intentioned) and injected to help the agent — but doesn't help it — is a waste of tokens but even injected context that when I read it sounds useful can oversteer the model and make it second guess or take a more complicated route than it normally would (you can see this when looking at traces with and without that injected context) often harnesses also mention in their syst…
I am super curious how much in your opinion the extra prompting is useful?
>often harnesses also mention in their system prompt locations of markdown files that the model can consult if the model thinks they might help >that hint alone as part of the system prompt can be strong enough to make the model read in more tokens than would have been necessary
I purposefully do this as I imagine it is useful. In my project I am seeing solid adherence to norms and a deep capacity to iterate on completed features. Essentially for each feature I have the model make a {featureName}.AGENTS.md at the root folder of the feature, where it maintains what is going on.
I am moving between Claude Code and Codex atm, but I began this pattern when pi + kimi 2.6 was my main driver.
Re: Cursor removed cost information from the usage page and CSV export
#133They also just ended their referral program without any announcement or warning - referrals page on my account just disappeared, all whilst I'm sending them free traffic.
I guess this is to be expected of a now Elon Musk (that Nazi salute guy) owned company. It's a shame - the product was great.
Re: Cursor removed cost information from the usage page and CSV export
#134Earlier quoted context omitted.
> Do not underestimate how much popular harnesses are spamming the context window. The context window is very important. Do we have any insight into whether it is actually spam and not useful info such as project or programming language specific context?
in my book anything that is (I'm sure well intentioned) and injected to help the agent — but doesn't help it — is a waste of tokens but even injected context that when I read it sounds useful can oversteer the model and make it second guess or take a more complicated route than it normally would (you can see this when looking at traces with and without that injected context) often harnesses also mention in their syst…
> in my book anything that is (I'm sure well intentioned) and injected to help the agent — but doesn't help it — is a waste of tokens
How do you tell, though? I guess what I'm asking is: the data you presented shows some crazy differences, but the token burn alone doesn't tell us enough. What was the output of the task like? Did the harnesses that burned fewer tokens give you as good a result as the ones that burned more?
I guess it's subjective, of course, but nearly everything about LLM use is...
Re: Cursor removed cost information from the usage page and CSV export
#135Earlier quoted context omitted.
Claude Code injects a ton of tools into the system prompt, including their “memory system” that’s like 10k+ tokens. Depending on your task shape, this can easily double your task cost (e.g. a low context-using job that takes many turns, like a monitoring loop). You should use --disallowed-tools to prune any tools not needed for the task. Note that this is also a perpetual game of whack-a-mole since they’re always add…
> Claude Code injects a ton of tools into the system prompt It's so unfortunate they don't let you use the subscription with other harnesses anymore - since even if I used OpenCode they'd still get a bunch of useful data from the API calls, meanwhile I could stretch their tier limits way further.
The funny thing is that in some cases using a different harness with the subscription plan could actually be very good for Anthropic: e.g. if I were to use smol with Opus, it could use fewer tokens than CC for the same task. People on subscription plans burning fewer tokens is a good thing for Anthropic.
The only downside for Anthropic that I can see is that hitting your limits more often (while using CC) could make you want to upgrade plans, and a more efficient harness could keep you from doing that. But I can't imagine the cost (to Anthropic) of those inefficient tokens is worth it to them.
Re: Cursor removed cost information from the usage page and CSV export
#136Earlier quoted context omitted.
> Do not underestimate how much popular harnesses are spamming the context window. The context window is very important. Do we have any insight into whether it is actually spam and not useful info such as project or programming language specific context?
in my book anything that is (I'm sure well intentioned) and injected to help the agent — but doesn't help it — is a waste of tokens but even injected context that when I read it sounds useful can oversteer the model and make it second guess or take a more complicated route than it normally would (you can see this when looking at traces with and without that injected context) often harnesses also mention in their syst…
To be fair, 5.6 Sol is pretty much doing a ton of reasoning you can't see (and which you don't think about the cost of if you're using it via an OpenAI Pro subscription)
Re: Cursor removed cost information from the usage page and CSV export
#137Earlier quoted context omitted.
> Claude Code injects a ton of tools into the system prompt It's so unfortunate they don't let you use the subscription with other harnesses anymore - since even if I used OpenCode they'd still get a bunch of useful data from the API calls, meanwhile I could stretch their tier limits way further.
It's so unfortunate people don't realize it's cheaper to write their own well working agent instead of insisting with general purpose bloated ones like Claude. 200$/month is a lot of money on Luna/DS4 flash, like really a lot and the results are much better than clowning on bloated CC. It's absurd how you have more and more organizations encoding their processes on LLMs and "engineers" (charlatan coders) don't even b…
I have yet to spend $200 on DS4 after two months of using it with an entire team.
Re: Cursor removed cost information from the usage page and CSV export
#138Earlier quoted context omitted.
Code and reasoning generated by Opus/Fable via Cursor seems to be quite better than Claude Code's for the same prompt.
Does that mean you’re paying api prices + cursor markup (?), or can you somehow piggyback on your Claude subscription? Fable via the API is really too expensive
[dead]
Re: Cursor removed cost information from the usage page and CSV export
#139I was an early and passionate adopter and paying customer of Cursor (since 2023!), but it’s probably been 6 months since I opened it. These days I “write” code with claude code and codex, and read/review it on GitHub. If I need to read it locally, I use a plain text editor. Can someone help me understand what value cursor offers in 2026?
Cursor Tab is nice when you're hand-editing stuff. Not sure it's worth $20 though. I'd totally buy and forget a $5 Cursor subscription just for Cursor Tab. The $20 price point is just too competitive now and I'd rather use the Claude/Codex plugin over Cursor's agentic coding sidebar.
cheap cursor tab on its own would be so nice
Re: Cursor removed cost information from the usage page and CSV export
#140I can only recommend to regularly measure how many tokens a harness+model combination uses for a certain task There are huge token efficiency/bloat differences between agents while working on the same tasks, using the same model, in the same environment Yesterday I ran 10 agentic tasks using GPT 5.6 Sol in an ubuntu 26.04 vm a couple of times with different harnesses and got vastly different token usage. +-----------…
I think it’s too easy to trick you into token counting by checking tokens used. I think we should only focus on Price, time and productivity. Some kind of ratio
So a cheap model with many tokens or an expensive model with much less tokens could potentially be same price.
Maybe only time will be the differential factor.