

People have complained about this for as long as computers existed. It’s not a new development and not exclusive to LLM usage.


People have complained about this for as long as computers existed. It’s not a new development and not exclusive to LLM usage.


Input tokens are cheap, those shouldn’t cause your quota to run out too quickly. What you can try is using some sort of YAGNI enforcement like the Ponytail plugin. Also giving some instructions in your personal AGENTS.md for the model to give more efficient answers can help.
What plan are you using? Currently I think that ChatGPT plus can be a bit tight if you’re not careful. On my Claude plan for work I can use Opus all day and it barely scratches the quota. I’m not sure which Team seat I have though, maybe it’s the premium one.


I answered the cost point


So you’re using a really crappy model for agent work and extrapolate all the problems you encounter to actually capable models? That’s not really how anything works.
If Cursor is this bad with quotas, get a ChatGPT or Claude subscription. The $20 tiers are fine even for large codebases. For extended autonomous work (goal or loop mode) you would want the higher tiers. Use at least Terra 6.1 or Sonnet 5.5 for your regular conversation and if needed, let them create cheaper subagents for large, repetitive tasks.


I’ve played more amazing games this year than ever before and my backlog still keeps growing. Indie gaming is alive and well.


It’s just the usual annoying cynicism that people need to express in every single post


It’s terrible to have everybody have a bunch of the world’s limited supply of money instead of shoving it all into one guy’s pocket
Might’ve been a bait and switch during other activities


It works and I’ve been playing around with it for the past week. Not really knowing what I’m doing, because my background is in software development, not reverse engineering, I’ve been running into the usual problems with badly guided agents. My project is cluttered, I don’t really know what’s important, progress is rather slow. But there is progress and I’m sure someone with more RE knowledge can make the process more efficient.
I’m looking forward to getting some of my favourite old games running on modern systems using this.
Even if it was true that people didn’t spend on art anymore, which it isn’t, that’s still an appeal to hipocrisy. You may not have enough leftover money to spend on unique art pieces, which I consider to be a luxury, but you can still critique the emergence of generative, generic art.


Yeah it was available in the beta branch already
Well you could say his mental illness forces him


It’s just a super weird article. It goes into extreme detail randomly, mentioning specific function names and memory mechanisms, but doesn’t explain any of it.
This happens when an LLM reads a bunch of pages with stuff it doesn’t have much internal knowledge about, and then tries to summarize that into an article.


I prefer a GUI for most stuff. They’re way more discoverable, you don’t have to memorize cryptic flags, and the mouse is just the more efficient input device to me.
Still I can use a terminal if I have to, that’s just part of the job to me.
That must be the leftover from the Brutalismus 3000 cover photo.
This is not a debate. What is going on in the comments of this post, can you not spot a joke?
That’s part of the joke, it sets you up with the wrong expectations


That’s not my experience but I’m not trying to run Windows on a 30 year old computer.
That wasn’t the implication. The comment above mine could be read in a way that suggests, declining software and systems quality has suddenly emerged from LLM usage. I was trying to highlight, that this has forever been thrown around as an anecdote. I hope, that someone reading my comment would think more thoroughly about their experience with software over the years and how their own perceptions and bias might have changed through that time.