Skip to content

Instantly share code, notes, and snippets.

View zhanglpg's full-sized avatar

Liping Zhang zhanglpg

  • Alibaba Group Inc
  • San Francisco Bay Area
View GitHub Profile
@zhanglpg
zhanglpg / Alibaba-Agentic-Infra-Unified-Architecture.md
Last active April 2, 2026 08:20
阿里巴巴 Agentic 基础设施 — 统一架构设计
title 阿里巴巴 Agentic 基础设施 — 统一架构设计
date 2026-04-02
tags
ai-infrastructure
agentic-systems
alibaba
architecture
strategy
self-improvement
evals

阿里巴巴 Agentic 基础设施 — 统一架构设计

定位: 从研发基础设施到百万级 Agent 运行平台,一个统一的技术架构与演进路线。 >

@zhanglpg
zhanglpg / Miessler-AI-Ideas-and-Agentic-Infra.md
Last active April 2, 2026 05:54
Miessler 的五个 AI 核心命题与 Agentic 基础设施设计
title Miessler 的五个 AI 核心命题与 Agentic 基础设施设计
date 2026-04-02
source https://danielmiessler.com/blog/the-most-important-ideas-in-ai
tags
ai-infrastructure
agentic-systems
self-improvement
evals
intent-engineering

Miessler 的五个 AI 核心命题与 Agentic 基础设施设计

Daniel Miessler 在 2026 年 3 月底提出了五个他认为当前 AI 最核心的观念。读完后我意识到,这五个命题不只是"观察"——它们是 agentic 基础设施的设计约束。如果你在造一个百万级 agent 平台,这些不是观点,是物理定律。

@zhanglpg
zhanglpg / baba-institutional-research.md
Created March 22, 2026 02:31
BABA Q3 FY2026 Earnings - Institutional Reactions Research (Fact-Checked)

BABA Q3 FY2026 Earnings — Institutional Reactions Research

Earnings Date: March 19, 2026
Research Date: 2026-03-22
Fact-Check Date: 2026-03-22
Reliability Score: ~90% (Core data verified)


📊 Executive Summary

@zhanglpg
zhanglpg / 2026-03-22-brief.md
Created March 22, 2026 01:48
Daily Portfolio Brief - March 22, 2026

Daily Portfolio Brief - March 22, 2026

Market Snapshot

Symbol Price Change Sector
SPY $659.80 -0.25% US Broad Market
QQQ $593.02 -0.32% Nasdaq 100
AAPL $248.96 -0.39% Tech
GOOGL $307.13 -0.18% Tech
@zhanglpg
zhanglpg / microgpt.py
Created March 7, 2026 21:57 — forked from karpathy/microgpt.py
microgpt
"""
The most atomic way to train and run inference for a GPT in pure, dependency-free Python.
This file is the complete algorithm.
Everything else is just efficiency.
@karpathy
"""
import os # os.path.exists
import math # math.log, math.exp