3dtours/penguin-harness
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(blog): grouped list, pinned posts, author/date/copy-link metadata (#20)

Browse Source 
Co-authored-by: Alice <alice@prismshadow.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Yaowei ZhengAliceClaude Fable 5
 authored and GitHub committed 2026-07-22 22:22:02 +08:00
1 parent 85f8b9bf1a
commit 3806e4e441
14 files changed
+314 -49
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

packages/landing/content/blog/local-agents-on-amd-gpus.en.md
+2 -1
View File
@@ -1,7 +1,8 @@
---
title: "A closer look at PenguinHarness — and running a self-improving agent locally on an AMD GPU"
date: 2026-07-20
category: news
category: practice
author: Ning Zhang (AMD), Yuyang Gao (AMD), Yaowei Zheng (PrismShadow)
excerpt: What PenguinHarness actually is, the ideas behind its architecture, and a real end-to-end run — a local open-weight model on an AMD GPU that fails a scored task, then improves itself from 0 to 4 out of 5 by editing its own files, entirely on-device.
---