From b3741af4e52191dce79fdb694ce0c870721d7445 Mon Sep 17 00:00:00 2001 From: Paul Gauthier Date: Sat, 1 Jul 2023 15:27:44 -0700 Subject: [PATCH] copy --- docs/benchmarks.md | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/docs/benchmarks.md b/docs/benchmarks.md index 0e0ea5260..e7dd4dab8 100644 --- a/docs/benchmarks.md +++ b/docs/benchmarks.md @@ -55,9 +55,7 @@ Using more complex output formats seems to introduce two issues: - It makes GPT write worse code. Keeping the output format simple appears to allow GPT to devote more attention to the actual coding task. - It reduces GPT's adherence to the output format, making it more challenging for tools like aider to accurately identify and apply the edits GPT is attempting to make. -I expected the new function calling API to make -structured output formats more reliable. -I was planning to adopt it in aider for both GPT-3.5 and GPT-4. +I was planning to start using a function call based edit format in aider for both GPT-3.5 and GPT-4. But given these benchmarking results, I won't be adopting the functions API at this time.