This is an automated email from the ASF dual-hosted git repository.
davsclaus pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/camel-website.git
The following commit(s) were added to refs/heads/main by this push:
new f7eab1db Blog: say what was wrong in the benchmark post intro
f7eab1db is described below
commit f7eab1dba2b91b4109dacba4cafc77231dbb7c8c
Author: Claus Ibsen <[email protected]>
AuthorDate: Tue Sep 15 20:36:47 2026 +0200
Blog: say what was wrong in the benchmark post intro
"was also wrong for a person" left it unclear whether the model or
Camel was wrong until the "Who benefits" section. Name Camel as the
subject up front.
Co-Authored-By: Claude Opus 5 (1M context) <[email protected]>
---
content/blog/2026/09/camel-local-model-benchmark/index.md | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/content/blog/2026/09/camel-local-model-benchmark/index.md
b/content/blog/2026/09/camel-local-model-benchmark/index.md
index 286bd537..d5aa964b 100644
--- a/content/blog/2026/09/camel-local-model-benchmark/index.md
+++ b/content/blog/2026/09/camel-local-model-benchmark/index.md
@@ -10,7 +10,7 @@ preview: "A frontier model ran the harness, a 22 GB local
model on a laptop did
Everyone claims their tool "works with any LLM". We wanted a number instead of
a claim, so we measured two very different models on the same Camel tasks, on
one laptop, with the same tooling. Then we did something more useful than
reporting the score: we ran the weaker model twenty times over two days, and
between every run we fixed whatever in Camel had made it fail.
-The interesting result is not which model won. It is that nearly everything
the losing model tripped over was also wrong for a person.
+The interesting result is not which model won. It is that nearly everything
the losing model tripped over was a problem in Camel, an unclear message or a
tool that did not say what to write, that would have tripped up a person as
well.
## The setup
