Yaowei Zheng | LlamaFactory

@code_hiyouga

70k ⭐️ OSS @llamafactory_ai, CTO @prismshadow_ai, ex-@ByteDanceSeed_ Building PenguinHarness - Best Self-Improving Harness. Opinions are my own.

github.com/hiyouga

Joined July 2024

Replies Reposts Media Articles

Pinned
Yaowei Zheng | LlamaFactory
@code_hiyouga
Jul 21
AI agents shouldn't be built by hand—but today's harnesses are still designed for humans. We just open-sourced PenguinHarness 🐧 A self-improving harness from the LlamaFactory team. → Let agents create and optimize other agents → Turn one prompt into a RAG app for just $0.02
00:00
11
Yaowei Zheng | LlamaFactory
@code_hiyouga
Sep 27
Anthropic has published a long-form article on RSI, “When AI builds itself,” using internal data for the first time to show how AI is already accelerating AI development. Claude writes over 80% of Anthropic’s code. Researcher output has roughly quadrupled. Models achieved a 52×
When AI builds itself
From anthropic.com
5
Yaowei Zheng | LlamaFactory
@code_hiyouga
Sep 26
A skill worth trying: anything2explainer. I give it a topic, and it generates the script, voiceover, subtitles, and animation. I used it to make the on-device RSI video below.
00:00
6
Yaowei Zheng | LlamaFactory
@code_hiyouga
Sep 25
GPT-6 Astra got more proofs right at high than at medium in Vals AI's ProofBench v1.1 tests. Each turn cost about $0.70 more, but 117 fewer turns made the whole run cheaper. Vals tested Astra, Claude Opus 5, and Opus 5.5 at five reasoning levels, from low to max. Opus 5.5 scored
2
Yaowei Zheng | LlamaFactory
@code_hiyouga
Sep 25
How many of these Jev demos are false advertising? The Minecraft post says the movement is “only possible” with Jev’s near-instant decisions. An Ender Dragon kill in 8:43, under $1. Sounds impressive. (Image 1) Then you look at Feitian Shanke’s breakdown: 129 of 165 Jev calls
2