diff options
| author | Willy Tarreau <w@1wt.eu> | 2026-08-02 22:35:39 +0200 |
|---|---|---|
| committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2026-08-04 16:24:50 +0200 |
| commit | 3d7c44f73765d98665fb97a4fb89c002c88ba1b9 (patch) | |
| tree | 7639d2f30bc1bd117f254042b08447cd02657111 /tools/perf/scripts/python | |
| parent | e447f7f33fa0a50d42d0539c161a662e67bd1a2c (diff) | |
docs: coding-assistant: explain important steps when looking for bugs
Due to the increasing capabilities of available AI models, it's becoming
common to see them used to find bugs anywhere. Unfortunately the quality
of reports (especially when they're believed to be security relevant) is
still lacking a lot.
Let's add a section dedicated to bug finding, explaining the few
mandatory steps (noting commit ID, writing the fix from the session that
found the bug, building and testing, etc). This was tested both against
Qwen3.6-27B-Architect-Polaris2-Fable-B-F451 running under Hermes, and
Opus-5, and both followed the instructions to the letter, verifying
their results and checking threat-model.rst to decline the vulnerability
aspect. At least in the current form it's expected to improve the
situation a little bit.
Cc: Greg KH <greg@kroah.com>
Signed-off-by: Willy Tarreau <w@1wt.eu>
Link: https://patch.msgid.link/20260802203540.3453-5-w@1wt.eu
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Diffstat (limited to 'tools/perf/scripts/python')
0 files changed, 0 insertions, 0 deletions
