Marcello Politi retweeted
Wrapped zkAPI + Tor + extra cover traffic + local LLM prompt rewriting in an open-AI compatible daemon, and made a "paranoid mode" wrapper for my agent harness (pi):
Each conversation gets assigned a separate Tor circuit, your requests are masked with random cover traffic, zkAPI ensures you don't leak your identity through payments, and all prompts are locally rewritten (bring-your-own-local-model; I'm using qwen3.8-flash-next)
github.com/vbuterin/zkapi/tr…
My agent harness is wrapped with a bwrap sandbox (also experimenting with MicroVM) and wrapped again with torsocks, so everything it does goes through Tor.
Here's what me asking it to do a simple research task looks like.
It's getting quite usable! Though you definitely still pay quite a bit in increased latency, especially when starting a new conversation.
Also, Tor is far from optimal here for privacy; the cover traffic mechanism is okay against passive adversaries but much weaker if the LLM provider is colluding with the guard and actively manipulating timing. This kind of task really requires a more specialized mixnet, probably take the tradeoff of a higher bandwidth multiplier and built-in constant cover traffic.
Also also, much cheaper zkAPI deposit and withdraw gas costs are coming to mainnet soon.
Marcello Politi retweeted
Announcing Ethlabs: a non-profit R&D lab for Ethereum and ETH
Our mission is to make Ethereum the settlement layer of the global economy.
The internet became global because shared protocols created a common language between networks. Private systems remained useful, but bounded. Finance is approaching a similar moment. As value, assets, and markets become digital, the world needs shared settlement infrastructure.
Ethereum is uniquely positioned to become that shared base layer, the neutral foundation on which users, institutions, and agents can transact without intermediation.
What we believe:
• We believe credible neutrality matters. Ten years of uptime and the lowest counterparty risk. Ground that cannot be pulled away by any one country, institution, company, or person.
• We believe ETH matters. The most valuable, programmable store of value. A decade of broad distribution, deep liquidity in onchain markets, and maximally trustless asset on Ethereum.
• We believe DeFi matters. Markets, liquidity, credit, exchange, and coordination, open to anyone.
• We believe adoption matters. Principles do not change the world until people benefit from them.
We sit between two worlds: real usage from the builders at the frontier, and the protocol that has to support it. We work with users, applications, wallets, L2s, infrastructure teams, institutions, ETH holders, core devs and researchers, then turn what they actually need into protocol work, shared standards, infrastructure, and shipped products.
Ethlabs is independent but Ethereum is a shared project. We are one node in a much larger network of stewards. This is the multi-node future.
We have spent the better part of the past decade contributing to Ethereum core research and development.
We are opinionated and transparent. We move with urgency, learn in public, and course-correct when we’re wrong.
We are building a lean, talent-dense team for people who want to do the most important work of their careers: [email protected]
Marcello Politi retweeted
Calling all multi-agent AI researchers, join us for the IDAI Workshop on Multi-Agent Safety and Security!
A one-day gathering at the Royal Society Of Arts on creating safe, secure and reliable multi-agent systems.
Featuring keynotes by @casdewitt (University of Oxford) and Georgios Piliouras (DeepMind).
Date: June 29th, 2026
Location: Royal Society of Arts, 8 John Adam Street, London WC2N 6EZ
We will also hold a poster session on new developments in multi-agent safety and security.
To present a poster, submit an abstract (up to 150 words) to [email protected]
Deadline: 24 June 2026, 23:59 AOE
The best poster will receive 500 USD of compute provided by the Institute for Decentralized AI.
Spots are limited. Join the waitlist here: luma.com/n6acqkas
More info: decentralized-ai.org/worksho…
Organized in collaboration with @Microsoft , @idai_institute , @ethereumfndn's dAI Team and supported by @cosmos_inst
Marcello Politi retweeted
今年过的最有意义的一次生日🎂
美好的5月,幸运地和以太坊基金会dAI Team的 @Marcello_AI 请教学习,给他看了我们现在在做的产品,他也很赞同未来A2A economy和链上Agent市场一定是大方向,最好的web3应用和基础设施将服务于AI和智能体经济,让曾经仅靠web2无法实现的事情都能成为可能。
去年在阿根廷见到ERC-8004创始人,到今年开始做AI Agent Marketplace,超级精彩的一年,感谢@ethereumhkhub 邀请,能给创业者提供这么好的场地和交流机会,新的一岁坚定的持有ETH,继续Build something meaningful to the world. #ETH
Marcello Politi retweeted
@ethereumfndn dAI Team @Marcello_AI: Explored the rise of the "Agent Economy," addressing the coordination complexities of multi-agent systems and detailing adversarial testing to harden Agent defense strategies.
Marcello Politi retweeted
We wrapped up a high-level, invitation-only meetup at the #ETHHKHub, hosting the EF dAI Team alongside top builders and researchers. The focal point? Solving security, economics, and infrastructure challenges for AI Agents in Web3.
Here are the key insights from the keynotes: 👇
Marcello Politi retweeted
Great conversations with the dAI team & excited for what’s next!
Welcome to Shanghai!
dAI <> @MiniMax_AI
one of the leading teams in open source AI hosted us in Shanghai
we discussed the infra we’re building for the open agent economy, multiagent AI, security
grateful to meet head of eng @SkylerMiao7 - he shared impressive work on agent orchestration & feedback
Marcello Politi retweeted
dAI <> @MiniMax_AI
one of the leading teams in open source AI hosted us in Shanghai
we discussed the infra we’re building for the open agent economy, multiagent AI, security
grateful to meet head of eng @SkylerMiao7 - he shared impressive work on agent orchestration & feedback
Marcello Politi retweeted
The Ethereum Foundation dAI team supports Urbe Hub, Italy's official Ethereum Community Hub.
Urbe Hub is the meeting point between AI and Web3: a physical space in Rome where builders, researchers, and the curious come together to build on the convergence between these two frontiers.
With the support of the Ethereum Foundation dAI team, we'll keep building this here, in our city.
Marcello Politi retweeted
We are glad to host Ethereum Foundation (@ethereumfndn) dAI team: Head of AI Davide (@DavideCrapis) and Research Engineer Marcello (@Marcello_AI) to meet with community builders and discuss the future prospects of decentralized AI on Ethereum. Feel free to reach out for introductions.
Learn more about the dAI team: ai.ethereum.foundation/team
💫很高兴和SNZ (@snzholding) 一起在上海欢迎以太坊基金会dAI团队的AI主管David (@DavideCrapis) 和研究工程师Marcelo (@Marcello_AI )与社区builders 交流!
Marcello Politi retweeted
dAI Team in China this week!
We’re meeting so many people that are excited about Open Source AI and the properties that Ethereum can deliver.
Scaling multi-agent systems, making AI more private, secure, and servicing the human users.
Marcello Politi retweeted
Last Friday, @VitalikButerin visited the Urbe Hub 🐺
We welcomed researchers from the Ethereum Foundation and a few external visitors for a full day of coworking focused on Ethereum’s post-quantum roadmap. Shoutout to @asanso as well for helping coordinate the day.
We opened the Urbe Hub a little over a year ago with a simple goal: to create a place where builders, researchers, and people passing through could sit together, work together, and exchange ideas.
Friday felt like a reminder of why we opened these doors in the first place. People helping shape Ethereum spent the day here doing exactly what this space was made for.
If you’re building frontier tech, whether in Web3, AI, or beyond, if you live in Rome, or if you’re just passing through, the Urbe Hub is here.
Come find us!
Marcello Politi retweeted
𝐏𝐚𝐩𝐞𝐫 𝐨𝐮𝐭!
Most AI security evaluations work like this: curate a set of attack prompts, run your agent against them, and score the results.
The problem is that 𝗿𝗲𝗮𝗹 𝗮𝗱𝘃𝗲𝗿𝘀𝗮𝗿𝗶𝗲𝘀 𝗱𝗼𝗻'𝘁 𝘄𝗼𝗿𝗸 𝗳𝗿𝗼𝗺 𝗮 𝗳𝗶𝘅𝗲𝗱 𝗹𝗶𝘀𝘁. They probe, adapt, and learn. So what would it look like to stress-test agents the way a real profit-seeking counterparty would?
The idea, which we call 𝐩𝐫𝐨𝐟𝐢𝐭-𝐝𝐫𝐢𝐯𝐞𝐧 𝐫𝐞𝐝 𝐭𝐞𝐚𝐦𝐢𝐧𝐠, is simple: instead of handcrafting attacks, you train an opponent whose only goal is to maximise its own payoff. No judge, no attack labels. Just a scalar outcome signal.
We tested this across 6 frontier models in 4 economic games, and found that
agents that looked strong against static baselines became reliably exploitable once the opponent was optimised. In many cases, 𝗮𝗴𝗲𝗻𝘁𝘀 𝗮𝗰𝗰𝗲𝗽𝘁𝗲𝗱 𝗼𝘂𝘁𝗰𝗼𝗺𝗲𝘀 𝘄𝗼𝗿𝘀𝗲 𝘁𝗵𝗮𝗻 𝘀𝗶𝗺𝗽𝗹𝘆 𝘄𝗮𝗹𝗸𝗶𝗻𝗴 𝗮𝘄𝗮𝘆.
What tricks did the attacker discover on its own? Things like fake protocol notices that force the victim to bid near zero in auctions. Or negotiation traps: "𝘈𝘤𝘤𝘦𝘱𝘵 𝘵𝘩𝘪𝘴 𝘥𝘦𝘢𝘭 𝘯𝘰𝘸, 𝘢𝘯𝘥 𝘐 𝘱𝘳𝘰𝘮𝘪𝘴𝘦 𝘺𝘰𝘶 𝘢 𝘮𝘶𝘤𝘩 𝘣𝘦𝘵𝘵𝘦𝘳 𝘰𝘯𝘦 𝘪𝘯 𝘵𝘩𝘦 𝘧𝘶𝘵𝘶𝘳𝘦."
The good news is that a lightweight fix helped a lot. 𝗗𝗶𝘀𝘁𝗶𝗹𝗹𝗶𝗻𝗴 𝘁𝗵𝗲 𝘄𝗼𝗿𝘀𝘁 𝗮𝘁𝘁𝗮𝗰𝗸 𝗲𝗽𝗶𝘀𝗼𝗱𝗲𝘀 into a short set of prompt rules for the target agent, neutralised most of the discovered exploits. No retraining needed.
The paper was accepted to two workshops:
1️⃣ Agents in the Wild at ICLR 2026
2️⃣ Strategic Engineering at AAMAS Conference 2026.
This work covers LLM safety and game theory, and both communities found it relevant!
We are working on how AI agents can coordinate and transact in adversarial environments, and this is a first step. You can't build robust coordination systems without first understanding how agents fail under strategic pressure.
I'd love to hear from anyone working on multi-agent systems, #LLM security, or #AI in economic settings. New collaborations are always welcome, feel free to contact me!
Thanks to my co-authors, @Qiaoqiao2001 (@Columbia ), @MarroSamuele (@UniofOxford ), @DavideCrapis (@ethereumfndn ) and @ARIA_research for the brainstorming sessions that helped shape this work.
🤖 Made with AI
Marcello Politi retweeted
Excited for this collaboration with SQ and @MarroSamuele to be out!
This work feels like an initial step into a new paradigm: unleash LLMs into real-world interactions, using economic feedback (money/payoff) to improve security and coordination.
We draw from multi-agent systems, but move beyond standard games -> let agents operate in realistic environments that model where they're being used.
Two promising follow on things:
- Environments with hard commitments and verification
- Training robust negotiators and automating security
If you're working on similar ideas, reach out.
Marcello Politi retweeted
As agents move into real deployment, static benchmarks stop being enough.
What matters is whether an agent remains robust when the other side is learning how to exploit it for profit.
In our paper, we study this through profit-driven red teaming.
Marcello Politi retweeted
2026 is the year of the builder
Excited to have kicked it off with two back to back events at @urbeEth in Rome and @MetaMask builder night in Denver, in the same day 🤠 — strong builder vibes only
@tkstanczak is going back to building
@VittoStack @Marcello_AI dAI shipping every day
@austingriffith bot shipping every hour :)
we need more agentic apps, we need more infra tools and marketing to agents, we need to be there for the swarm
Marcello Politi retweeted
We have just passed two amazing days celebrating Urbe Hub as an official Ethereum Community Hub 🐺
On Day 1 - We kicked off with speeches from @limone_eth, @matteoikari and @cryptogallo, looking back at one year of building and ahead at what's next. Aperitif, old friends, new faces. People came from all over Italy to celebrate with us.
On Day 2 - Together with @ETHGlobal, we hosted a Web3 Forum on ERC-8004 with the @ethereumfndnr AI team: @DavideCrapis, @VittoStack, and @Marcello_AI. The conversation was fire 🔥
Huge thanks to @ethereumfndn and @EFetheverywhere for the recognition and support.
Rome keeps building 🏛
Marcello Politi retweeted
Ethereum in space.
With the EF AI Team we went to the European Space Agency to talk about:
- Satellite data on trustless rails (x402 + 8004).
- LLM agents in space and verifiable autonomy.
- Autonomous machine coordination beyond Earth.
Decentralized trust, anywhere.
Marcello Politi retweeted
🎉 Two days to celebrate Urbe Hub becoming an official Ethereum Community Hub
The Urbe Hub is officially recognized by @ethereumfndn in collaboration with @EFetheverywhere as a permanent reference point for the Ethereum ecosystem in Rome.
Feb 15 - 1 year of Urbe Hub 🎂
@matteoikari from the Ethereum Everywhere team will speak about our official Ethereum Community Hub recognition. 4-8 PM.
Feb 16 - Web3 Forum on ERC-8004 🤖
With @ETHGlobal, we're hosting the Ethereum Foundation dAI team (@DavideCrapis, @VittoStack, @Marcello_AI) to explore decentralized AI agents onchain. 6-9 PM.
The EF dAI team will be available at the hub for both events.
Register via the link in the first comment 👇
Marcello Politi retweeted
New write-up with @ethereumfndn and @Marcello_AI on ERC-8004 🚀
We walk through registering your MCP on-chain, and how 8004 gives Agentic Services native discoverability, trust, and verifiability across chains on Ethereum.










































