mirror of
https://github.com/Aider-AI/aider.git
synced 2025-05-31 01:35:00 +00:00
Update benchmarks.md
This commit is contained in:
parent
156c9f7300
commit
e65f10ce9d
1 changed files with 1 additions and 1 deletions
|
@ -42,7 +42,7 @@ This produced some interesting observations:
|
|||
|
||||
These results agree with an intuition that I've been
|
||||
developing about how to prompt GPT for complex tasks like coding.
|
||||
You want to minimize the "cognitive load" of formatting the response, so that
|
||||
You want to minimize the "cognitive overhead" of formatting the response, so that
|
||||
GPT can focus on the task at hand.
|
||||
You wouldn't expect a good result if you asked a junior developer to
|
||||
implement a new feature by hand typing `diff -c` formatted updates to the current code.
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue