dearwolf/aider
1
0
Fork 0
mirror of https://github.com/Aider-AI/aider.git synced 2025-06-03 03:05:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

copy

Browse source
This commit is contained in:
Paul Gauthier 2024-05-23 11:34:42 -07:00
parent b56aa129dc
commit bb2d5b2fbf
1 changed files with 6 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

12
_posts/2024-05-22-swe-bench-lite.md
View file

@ -161,7 +161,7 @@ Aider instead uses a
[repository map](https://aider.chat/2023/10/22/repomap.html) [repository map](https://aider.chat/2023/10/22/repomap.html)
to help the LLM understand the to help the LLM understand the
layout, code structure, and content of a git repo. layout, code structure, and content of a git repo.
The repo map is created from the code's The repo map is created through static analysis of the code's
abstract syntax tree and call graph abstract syntax tree and call graph
to provide a compact and powerful summary of the entire code base. to provide a compact and powerful summary of the entire code base.
The map is constantly The map is constantly
@ -169,7 +169,7 @@ tailored to show
repo context that is relevant to the current state of the chat conversation. repo context that is relevant to the current state of the chat conversation.
This is done by performing a graph optimization on the code's call graph. This is done by performing a graph optimization on the code's call graph.
When the user asks for a change to their code, the LLM uses the repo map When the user asks for a change to their code, the LLM can use the repo map
to decide which files to edit. to decide which files to edit.
The LLM simply returns a normal text response explaining which files The LLM simply returns a normal text response explaining which files
it needs to edit and why. it needs to edit and why.
@ -230,7 +230,7 @@ This is usually because the LLM has failed to conform to the editing
instructions in its system prompt. instructions in its system prompt.
When aider completes, it returns an editing outcome that indicates When aider completes, it returns an editing outcome that indicates
whether it was able to successfully complete all edits. whether it was able to successfully complete all edits.
The benchmark harness used this editing status as The benchmark harness uses this editing status as
one criteria to determine if aider has one criteria to determine if aider has
created a plausible solution. created a plausible solution.
@ -277,7 +277,7 @@ At completion,
aider reports a linting outcome that aider reports a linting outcome that
indicates if it was able to produce indicates if it was able to produce
code without any outstanding linting errors. code without any outstanding linting errors.
The benchmark harness used this status as The benchmark harness uses this status as
one of the criteria to determine if aider has one of the criteria to determine if aider has
created a plausible solution. created a plausible solution.
@ -309,8 +309,8 @@ that indicates if it completed with any outstanding failing tests.
The benchmark harness uses this status when deciding if aider The benchmark harness uses this status when deciding if aider
has produced a plausible solution. has produced a plausible solution.
To be clear, *aider cannot run or even see the held out "acceptance tests"* To be clear, *aider cannot run or even see the held out "acceptance tests"* that
that are used to determine if a proposed solution correctly are used to determine if a proposed solution correctly
resolves the problem. resolves the problem.
Those tests are only run outside of aider and the benchmark harness, Those tests are only run outside of aider and the benchmark harness,
to compute the final benchmark score. to compute the final benchmark score.