The ground-truth is the rudeness is load bearing at human machine interface.
Cursor removed cost information from the usage page and CSV export
41–50 of 172 posts
Re: Cursor removed cost information from the usage page and CSV export
#42I 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. +-----------…
Anything else I can read about smol?
also, are you using a tool to collect those metrics? what is it?
Re: Cursor removed cost information from the usage page and CSV export
#43Earlier 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…
The system prompt part is surely cached across all users.
You still pay cache token costs on API calls. Cache cost/token are 90% lower, but you pay it every single turn.
I’m not sure if they let you skip the cache write cost on the first turn. That would imply cross-user caching infrastructure or special casing the default system prompt to give you a discount. Maybe? Away from the computer but you could try a “hello” in a fresh session and see what was billed.
Re: Cursor removed cost information from the usage page and CSV export
#44I 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. +-----------…
Anything else I can read about smol? also, are you using a tool to collect those metrics? what is it?
smol is basically this 9 line python agent re-implemented in Go
https://news.ycombinator.com/item?id=49006862
I'll have more about it in the next hours/days, you can follow me on twitter in the meantime (https://x.com/__tosh)
Re: Cursor removed cost information from the usage page and CSV export
#45Earlier 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…
The system prompt part is surely cached across all users.
the system prompt still takes up useful space in the context window and steers the model into unnecessary actions and over-thinking patterns
Re: Cursor removed cost information from the usage page and CSV export
#46I 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. +-----------…
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…
ty re --disallowed-tools
for coding agents 'shell' is often all you need (just make sure the environment has the necessary tools)
Re: Cursor removed cost information from the usage page and CSV export
#47I 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?
I don't think it offers any. I got tired of switching between Codex and Claude plus I wanted to start using glm and kimi so I switch to pi. Then I got tired of VSCode eating up battery and RAM so I moved to Neovim which has barely any efficiency downside anymore since most code is not written by hand and if you know how to use it well it was only maybe 10% less efficient than VSCode to begin with. I am not sure why a…
Huh, never thought about that 2nd point - I'm also transitioning to pi, but didn't think to change to neovim as well. I guess your logic holds for claude code users as well though.
Re: Cursor removed cost information from the usage page and CSV export
#48[flagged]
LLM generated comments are banned on this site.
Re: Cursor removed cost information from the usage page and CSV export
#49I 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. +-----------…
What tools are you using to run the comparison? Or are you just running the prompts and checking them with something like ccusage?
I’m asking because I’ve been looking for agent harness comparison tools too. I’m interested in more than just the inputs and outputs—I also want the system prompts, traces, and tool calls. It’s useful to understand why Codex, for example, uses more tokens while Pi doesn’t.
Fewer tokens aren’t necessarily better if the agent skipped important checks. On the other hand, using more tokens could just mean it’s overthinking the process. Either way, seeing the full execution trace for the same task is really valuable.
Re: Cursor removed cost information from the usage page and CSV export
#50I 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?
The way they spin up multiple Composer 2.5 before sending it over to the model of your choice is nice.