This is an automated email from the ASF dual-hosted git repository. spectrometerHBH pushed a commit to branch blog/update-kernel-development-wording in repository https://gitbox.apache.org/repos/asf/tvm-site.git
commit 6a0dce517b7d8fcac8ec6291738e1b29f7797585 Author: spectrometerHBH <[email protected]> AuthorDate: Wed Nov 4 14:05:47 2026 -0500 Refine the opening sentence of the TIRx article --- _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?**
