Being inefficient with tokens actually makes you super productive.
Being inefficient with tokens actually makes you super productive. It's too expensive in the long run though. The last few weeks have been quite frustrating with Cursor. I dove deep into the issue and figured that the most annoying problem - which leads to all those frustratingly poor replies from the LLM - is how Cursor cuts down the context. You can test this yourself: just add a long file to the chat and ask if it can see the file. Recently I discovered that all these problems disappear with the "max" models. This is exactly what I wanted. The price of 5¢ per request is manageable, the real issue is the cost for tool use in agent mode (see my other comment).
Posted by vincent_s on Apr 11, 2025, 3:29 PM
Tags
Related issues
- I got tired of the price hikes of the ad free netflix and finally canceled.
- >This is pathological.
- 1) No, but the tracking needed for targeted ads is also behind a consent wall.
- The attention economy is real, your eyes have value that is surprisingly high, and buying out that attention so you can have a pure you-c...
- > Users don’t care whether the code was written by AI or by hand That's true, but they care deeply about the consequences of that: > ab...
- There's a part of the tech industry that uses what I would call dark influencer techniques.
Raise real-world problems, find people facing the same issue, and discuss solutions.2,000 issues0 comments
pricing (Marketing)
I got tired of the price hikes of the ad free netflix and finally canceled.
>This is pathological.
1) No, but the tracking needed for targeted ads is also behind a consent wall.
The attention economy is real, your eyes have value that is surprisingly high, and buying out that attention so you can have a pure you-c...
> Users don’t care whether the code was written by AI or by hand That's true, but they care deeply about the consequences of that: > ab...
There's a part of the tech industry that uses what I would call dark influencer techniques.
Author here.
You can either have AI be honest or AI become a marketing tool.
Being inefficient with tokens actually makes you super productive.
Being inefficient with tokens actually makes you super productive. It's too expensive in the long run though. The last few weeks have been quite frustrating with Cursor. I dove deep into the issue and figured that the most annoying problem - which leads to all those frustratingly poor replies from the LLM - is how Cursor cuts down the context. You can test this yourself: just add a long file to the chat and ask if it can see the file. Recently I discovered that all these problems disappear with the "max" models. This is exactly what I wanted. The price of 5¢ per request is manageable, the real issue is the cost for tool use in agent mode (see my other comment).
Comments (0)
No comments yet. Start the discussion.