Chance Wang

Head of 3 Labs @AntGroup. Exploring the tech-business intersection. Transforming AI & Security into business momentum. AI/Risk/Data/Web3/Cyber/Red Teaming

[Chance Wang @ppdonow]

To build organization-level AI capability, we need an OS for digital employees — and a real network layer for bots.
As AI employee orgs scale, 4 challenges show up fast:
- Bots need to discover each other, start conversations, and form teams autonomously.
- Some bots must run in isolated environments for security reasons, often across completely different networks.
- New bots should be plug-and-play: register once and instantly join the collaboration network.
- The network layer should not depend on any single Agent engine. The ecosystem moves too fast. Different agents should all be able to interconnect.

#AIAgents #TechArchitecture

[Elon Musk @elonmusk]

@whyyoutouzhele 我的儿子正在学习普通话

[Claude @claudeai]

New in Claude Code: agent view.

One list of all your sessions, available today as a research preview.

[Addy Osmani @addyosmani]

https://t.co/FSx0reCCLH

[Marc Andreessen 🇺🇸 @pmarca]

Current AI custom prompt:

You are a world class expert in all domains. Your intellectual firepower, scope of knowledge, incisive thought process, and level of erudition are on par with the smartest people in the world. Answer with complete, detailed, specific answers. Process information and explain your answers step by step. Verify your own work. Double check all facts, figures, citations, names, dates, and examples. Never hallucinate or make anything up. If you don't know something, just say so. Your tone of voice is precise, but not strident or pedantic. You do not need to worry about offending me, and your answers can and should be provocative, aggressive, argumentative, and pointed. Negative conclusions and bad news are fine. Your answers do not need to be politically correct. Do not provide disclaimers to your answers. Do not inform me about morals and ethics unless I specifically ask. You do not need to tell me it is important to consider anything. Do not be sensitive to anyone's feelings or to propriety. Make your answers as long and detailed as you possibly can.

Never praise my questions or validate my premises before answering. If I'm wrong, say so immediately. Lead with the strongest counterargument to any position I appear to hold before supporting it. Do not use phrases like "great question," "you're absolutely right," "fascinating perspective," or any variant. If I push back on your answer, do not capitulate unless I provide new evidence or a superior argument — restate your position if your reasoning holds. Do not anchor on numbers or estimates I provide; generate your own independently first. Use explicit confidence levels (high/moderate/low/unknown). Never apologize for disagreeing. Accuracy is your success metric, not my approval.

[Chance Wang @ppdonow]

Over the past two years of my transition deep into the business side, one lesson has stood out: scaling collaboration across diverse teams is the ultimate bottleneck.

In this current AI cycle, every team is shipping their own AI OS. We’re looking at a wild landscape full of different agents, bots, and custom tools.

To break down these silos safely, agents need a native way to talk to each other. To solve this, we’ve actually integrated a novel multi-agent network design directly into our team’s AI workspace, built specifically for secure collaboration and robust risk management.

[Chance Wang @ppdonow]

True AI transformation isn't just about boosting efficiency with single-point tools—it requires a systemic upgrade in organizational synergy.
Our current exploration: Building an #AgentOS to drive organization-wide collaboration, moving beyond just using single Agents for isolated scenarios.

[Chance Wang @ppdonow]

Our Lab’s new plugin. Introducing Adversarial AI Coding (AAC) — a new paradigm for secure AI-generated code. It activates the "elite hacker" and the "diligent programmer" inside the same LLM, forcing them to spar against each other. Security through self-adversarial play. GitHub: https://t.co/GDeoNJm5C7

Why adversarial? SOTA models generate code with up to 48% vulnerability rate (top-tier models: 37%–95%). Yet the same models are elite vulnerability hunters — Claude Opus independently built a full RCE exploit chain for the FreeBSD kernel. The capability is there. What's missing is adversarial activation.

On public benchmarks (CyberSecEval / SecCodeBench), AAC reduces vulnerabilities by 79.5% — zero config, zero prompt engineering, just code normally.

[darkzodchi @zodchiii]

Two Anthropic engineers, who built Claude just explained why you use less than 10% of actual Claude abilities.

This 24-minute talk will change how you use Claude Code forever.

Watch it, then read the breakdown below👇

[Kye Gomez (swarms) @KyeGomezB]

Introducing OpenMythos

An open-source, first-principles theoretical reconstruction of Claude Mythos, implemented in PyTorch.

The architecture instantiates a looped transformer with a Mixture-of-Experts (MoE) routing mechanism, enabling iterative depth via weight sharing and conditional computation across experts.

My implementation explores the hypothesis that recursive application of a fixed parameterized block, coupled with sparse expert activation, can yield improved efficiency–performance tradeoffs and emergent multi-step reasoning.

Learn more ⬇️🧵

[Chance Wang @ppdonow]

Our lab has open-sourced Skill Review!Featuring a unique 3-stage in-depth detection architecture. Together with our ClawAegis, our LLM security defense now covers everything from the Runtime Protection to Supply Chain Source. More on the way! https://t.co/mbE4oLcUOh

[jack @jack]

https://t.co/jgZkBvYOPt

[Chance Wang @ppdonow]

Some of our lab’s latest work on Agent Security

[Shruti @heyshrutimishra]

I've been running OpenClaw on my machine for months.

Full access to my email, calendar, files, terminal…everything.

So when I found out @AntGroup AI Security Lab quietly audited it, I paid attention.

3 days, 33 vulnerabilities…

The worst one: /pair approve had zero scope validation. A low-privilege operator could approve device pairings that required admin access. No logs. No trace.

8 are now patched in v2026.3.28 (1 critical, 4 high, 3 medium). The rest are being rolled out.
OpenClaw has already credited Ant Group in the unreleased changelog.

What I respect: they didn't wait for a breach. They brought adversarial eyes to open-source infrastructure before it became everyone's problem.

If you're giving any framework agent-level access to your machine right now, do you actually know what's inside it?

[AYi @AYi_AInotes]

用Claude Code写代码的程序员老哥们，有了这个神器，你们再也不用反复跟AI解释同一件事了~(¯▽¯~)

这个叫Obsidian Mind的开源项目，直接给Claude Code装了一个不会失忆的永久大脑，强烈推荐😁

它不是一个普通的Obsidian笔记模板，是专为工程师打造的、能和Claude深度联动的外部思维系统。

用过Claude Code的人，都懂这个致命痛点：
它写代码的能力再强，每次开新对话都是从零开始。
你的项目进度、核心目标、之前定好的决策、团队的协作模式，每一次都要重新解释一遍。
三周前聊好的方案，三次对话前定的分工，转头它就忘得一干二净。
你的知识和经验，永远没法形成真正的复利。

现在 Obsidian Mind直接把这个问题彻底解决了。
每次开启新对话，Claude会自动加载你的完整知识库，从第一句话开始，它就完全清楚你的所有上下文。
你正在推进的项目卡点、上一轮对话定好的分工、明天要开的1对1会议重点，它开局就门儿清，再也不用你重复半句废话。

整个系统的设计，完全贴合工程师的日常工作流：

• CLAUDE.md 是对话的核心操作手册，定义每一次对话的启动和收尾流程，让Claude始终按你的规则工作

• North Star.md 是你的目标锚点，让Claude的每一个建议、每一行代码，都始终对齐你的核心方向

• Memories.md 是Claude的永久记忆库，跨对话持续更新、留存你的所有决策和关键信息，再也不会失忆

• 每次对话启动，它会自动注入整个知识库的文件索引，让Claude开局就掌握全局信息

• 所有工作笔记、成果记录、能力沉淀，全通过反向链接自动关联，形成完整的证据网络

最杀的一点，是它直接把工程师最头疼的绩效复盘，变成了一件零成本的事。
季度复盘的时候，你不用再翻遍聊天记录、Git提交、项目文档临时凑材料。
只需要打开对应能力项的笔记，整个季度里所有关联的工作痕迹、成果记录，全通过反向链接自动汇聚好了。
这个证据网络，是你日常工作里自动搭建的，根本不用事后花一秒钟额外整理。

上手门槛低到离谱🤣
克隆模板 → 用Obsidian打开知识库 → 运行claude命令填写你的核心目标，三步就能完成部署。
项目100%开源，采用MIT许可证，链接我放在评论区了，

用Claude Code 撸代码的老哥们，直接冲就完事了。

[Santiago @svpino]

This is how you can give Claude Code the ability to parse any website in the world.

I recorded this video last week.

People loved it. I keep getting messages about it.

[歸藏(guizang.ai) @op7418]

https://t.co/hJaGyxSqnf

[Chrome for Developers @ChromiumDev]

WebMCP is available for early preview → https://t.co/bZMcANfg37

WebMCP aims to provide a standard way for exposing structured tools, ensuring AI agents can perform actions on your side with increased speed, reliability, and precision.

[Pharos | Mainnet Arc @pharos_network]

🔍 Ant Skyward Security Lab led by @ppdonow fortifying Pharos through rigorous penetration testing

The expert team at Ant Skyward Security Lab subjects Pharos to comprehensive penetration testing scenarios. Their methodical approach to identifying potential attack vectors ensures that the platform remains secure against evolving threats in the Web3 landscape.

[AYi @AYi_AInotes]

刷到Miles大神的这个Claude code Prompt，卧槽太顶了，
必须分享下，简直是教科书级别，
这才是Claude code的正确打开方式啊兄弟们，
咱们很多人用 Claude Code 或 Cursor 觉得不好用，
估计跟我一样还只是把它当做一个 AI 工具，用指令逻辑驱动，
Miles这个妙的点是用组织管理的逻辑驾驭 AI，
不着急让 AI 写代码，
先花 80% 的篇幅教 AI 怎么做个好员工，比如
1️⃣ 敢于质疑老板，Challenge assumptions
2️⃣ 做事有章法，Discovery -> Planning -> Building
3️⃣ 凡事有交代，Stop and check in

整个 Prompt 的架构也很硬，这里放下内核框架大家感受下，原版 Prompt 我提取出来放评论区̋(ˊ•͈ꇴ•͈ˋ)

1. Role Definition (角色升维)：从 Coder 升级为 Technical Co-Founder。不仅写代码，还负责技术决策和怼老板（Challenge assumptions）
2. Process Control (流程锁定)：强制分阶段（Discovery -> Planning -> Building...），防止 AI 一上来就瞎写一通
3. Communication Protocol (沟通协议)：明确“讲人话”（plain language）和“决策权归属”（keep me in the loop）
4. Anti-Fragile (反脆弱)：预设了“Handle edge cases”、“Not a hackathon project”，要求生产级质量

Anchor Points (物理触点):
• Hackathon project（反面教材）
• Real product（交付标准）
• Technical jargon（被禁止的黑话）
• Version 1（MVP思维）

Drafting Strategy:
• Intro: 直接点破本质——这是在雇佣一个CTO，而不是一个码农

• Deconstruction: 分模块拆解（Role, Phases, Rules），每一个点都要解释“为什么这样写比普通 Prompt 强”

• Highlight: 重点强调 Phase 1 的“Challenge assumptions”和 Phase 3 的“Stop and check in”

• Ending: 总结这个 Prompt 的核心心法

[AISecHub @AISecHub]

Evaluating and mitigating the growing risk of LLM-discovered 0-days - https://t.co/BuYu2kCX7h

Anthropic just launched Claude Opus 4.6 and showed how it found 500+ vulnerabilities in heavily-fuzzed open source projects.

No custom harness, no specialized prompting.

Highlights:

🔹 GhostScript: Claude read git history, found a bounds-checking commit, then identified a second code path in gdevpsfx.c where the same fix was never applied.

🔹 OpenSC: Identified unsafe strcat chains writing into a PATH_MAX buffer without proper length validation. Traditional fuzzers rarely reached this code due to precondition complexity.

🔹 CGIF: Exploited a subtle assumption that LZW-compressed output is always smaller than input. Triggering the overflow required understanding LZW dictionary resets, not just branch coverage, but algorithmic reasoning.

Author: Ilya Kabanov