I wasted all my day trying to succeed on a simple tasks, no matter which model I was trying to use.
By the end of the day, I understood what was going on: cursor is cutting off my documents WITHOUT TELLING ME!!!
This lack of transparency not only kills my work, waste my time, vastly increased my requests without success in the end.
I am willing to consider this is a bug and not an attempt to cut on the costs on the part of cursor, but I would appreciate a quick fix to prove it.
Thank you !!!
Vincent
Note. For info, the doc was with
Tokens: 66070 (according to https://token-counter.app/anthropic/claude-3.5-sonnet)
While the model context window is supposed to be 200K
The mentioned cut off “Au bonheur des souris” is around 20% from the start of my document, which means the file availlable to Claude 3.5 was ONLY around 9642 TOKENS long.
Why can’t I use 10000 tokens, when I am supposed to have a model with 200 000 tokens available???
Why am I not informed of what is availlable for the model and what is not available???