This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tvm-site.git
The following commit(s) were added to refs/heads/main by this push:
new ec01ae56883 Refine the opening sentence of the TIRx article (#76)
ec01ae56883 is described below
commit ec01ae56883edb4dc39c927cba2915f28eedeca2
Author: Bohan Hou <[email protected]>
AuthorDate: Wed Nov 4 14:12:14 2026 -0500
Refine the opening sentence of the TIRx article (#76)
---
_posts/2026-11-03-rethinking-abstractions-in-the-agentic-era.md | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/_posts/2026-11-03-rethinking-abstractions-in-the-agentic-era.md
b/_posts/2026-11-03-rethinking-abstractions-in-the-agentic-era.md
index 8e68c1fb3f4..b5fd66aeeae 100644
--- a/_posts/2026-11-03-rethinking-abstractions-in-the-agentic-era.md
+++ b/_posts/2026-11-03-rethinking-abstractions-in-the-agentic-era.md
@@ -10,7 +10,7 @@ author: "Apache TVM Community"
## TL;DR
{: #tldr }
-In our [previous community
effort](https://blog.mlc.ai/2026/09/29/tirx-harness-an-open-compiler-harness-for-agentic-gpu-programming),
we showed that with little more than Opus 5.5 and a few presses of Enter, we
could produce production-quality B200 kernels that significantly outperform
existing baselines.
+In our [previous community
effort](https://blog.mlc.ai/2026/09/29/tirx-harness-an-open-compiler-harness-for-agentic-gpu-programming),
we showed that by leveraging Claude/Codex with just a few presses of Enter, we
could produce production-quality B200 kernels that significantly outperform
existing baselines.
This led us, as ML compiler practitioners, to revisit a fundamental question
from first principles: **Do we still need our beloved compilers?**
