dearwolf/aider
1
0
Fork 0
mirror of https://github.com/Aider-AI/aider.git synced 2025-06-01 18:25:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 5

copy

Browse source
This commit is contained in:
Paul Gauthier 2024-08-15 06:05:38 -07:00
parent 23f89f1d29
commit 6ef2b8c0fa
1 changed files with 16 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

17
aider/website/_posts/2024-08-14-code-in-json.md
View file

@ -97,7 +97,7 @@ document.addEventListener('DOMContentLoaded', function () {
if (isStrict) { if (isStrict) {
patternContext.strokeStyle = 'rgba(255, 255, 255, 0.8)'; patternContext.strokeStyle = 'rgba(255, 255, 255, 0.8)';
patternContext.lineWidth = 2; patternContext.lineWidth = 0.75;
patternContext.beginPath(); patternContext.beginPath();
patternContext.moveTo(0, 0); patternContext.moveTo(0, 0);
patternContext.lineTo(size, size); patternContext.lineTo(size, size);
@ -112,6 +112,21 @@ document.addEventListener('DOMContentLoaded', function () {
</script> </script>
## Abstract
The newest LLMs have explicit tooling and
support for returning properly formatted json responses.
While it is tempting to have LLMs use json tool or function calls to
return code or code edits, this is unwise.
LLMs write worse code when asked to wrap it in json, harming their ability
to correctly solve coding tasks.
Returning code as plain (markdown) text results in 6% higher scores
on a variant of the aider code editing benchmark.
Even OpenAI's newest gpt-4o-2024-08-06 with "strict" json support
suffers from this code-in-json handicap.
## Introduction
A lot of people wonder why aider doesn't have LLMs use tools or function calls to A lot of people wonder why aider doesn't have LLMs use tools or function calls to
specify code edits. specify code edits.
Instead, aider asks LLMs to return code edits in plain text, like this: Instead, aider asks LLMs to return code edits in plain text, like this: