#Crypto #Blockchain engineer #Defi #Bolivia 🇧🇴 #Cofounder @palmera_dao @hypersig_ Farcaster: https://nitter.cf/t.co/1ynCcba3Tq lens: @jozer
Switzerland
Joined April 2016
- Tweets761
- Following2.6K
- Followers397
- Likes1.7K
Pinned Tweet
Thanks @EthPrague, for the opportunity to talk about how we can enhance AA with custom modules, focusing on @palmera_dao’s hierarchical module.
Jozer 🌴 retweeted
dear @gnosispay,
i accept your apology, but it doesn’t address the consequences of exposing my identity, home address and contact details alongside my wallet addresses.
as your email acknowledges, this information could be used to identify and target me. My concern now goes beyond phishing, it’s my physical safety.
i don’t feel safe at home knowing this and am actively exploring moving to a new place. an apology won’t cover the potential relocation costs or the stress and disruption involved.
i’m requesting $10,000 in compensation for this distress and disruption, including the relocation expenses i anticipate.
my dms are open to discuss this request and provide a wallet address for payment if agreed.
Kind regards,
0xriim
We had a data breach affecting the system powering Gnosis Pay-branded cards (our B2C business line) that resulted in the exposure of certain customer information.
Everyone affected was sent an email today with full information.
We deeply regret that this happened. While funds were not affected, the security of personal information is just as important and we take full responsibility.
Additional measures are in place until the B2C platform involved is fully retired as planned on 20 December 2026. In the meantime we encourage everyone to be even more vigilant. We will never ask for your PIN or seed phrase, or ask you to move funds.
Further Details: gnosispay.com/blog/data-brea…
We encourage security researchers to communicate security vulnerabilities directly with us via [email protected]. The same rewards apply as to Gnosis Chain: immunefi.com/bug-bounty/gnos…
Jozer 🌴 retweeted
This is f*cking insane. SpaceXAI engineer:
“SpaceXAI pays me $1.2M a year because i know how to build 150+ GrokBot teams that ship 1200+ updates a day while i sleep.
I haven’t written code by hand in months. I set the rules, then check what the bots deliver.”
In a 1-hour livestream, she starts with an empty GitHub and zero bots. 72 hours later, her team has built a company run by bots.
Here’s the system:
step 1 → give each bot one clear role and its own computer in the cloud.
step 2 → teach it a task once. it saves the process as a reusable skill.
step 3 → connect the bots in one group chat so they can hand work to each other.
step 4 → set the rules, let the team run, then check what gets done.
Even the 4 a.m. run happens with your laptop closed.
GrokBot → skills → bot team → one group chat → a company that runs itself
SpaceXAI calls it “a persona, not a task.”
Anyone can open a new GrokBot chat. the real unlock is building a team that keeps working without you.
This 1-hour tutorial is worth more than most $2,000 agentic engineering courses.
Bookmark it and watch today
Then read the article below ↓
Jozer 🌴 retweeted
XO 2.0 is live. The YouTube of Prediction Markets.
→ Convictions: anyone can create a market from $10
→ Liquidity Rewards: $1M in USDC, paid daily
→ MODRA: our AI resolution engine now settles markets autonomously
The market you want to trade doesn't exist? Now you create it.
Jozer 🌴 retweeted
Anthropic engineer:
"At Anthropic, 90% of our engineers use loops and ‘dreaming’ to build self-improving agentic systems.
сlose the agent loop. give an agent a way to verify its own output."
in a 30-minute session, an Anthropic team member explains how to build an agent that improves itself.
Claude + loops + dreaming + CLAUDE.md - that’s the secret.
Watch the talk, then save the playbook below.
Everyone's still optimizing prompts. The real moat is loop engineering.
A prompt gets one good answer. A loop holds a 40-minute call together while the human wanders and changes their mind.
@usebland just raised $100M building exactly that.
The difference:
• most voice AI survives one scripted loop, then breaks the second a human goes off-script.
• Bland's agents engineer the whole loop - context held, judgment applied, call finished. 3.5M a week.
• full stack, in-house. Sub-400ms, 100+ languages, data that never leaves your walls.
Everyone else is tuning prompts on someone else's model and praying.
Bland engineered the loops for the calls they all hang up on.
Watch it ↓
Jozer 🌴 retweeted
Reminder: Tomorrow we'll be hosting an X Space with @ChainPatrol:
"From Infrastructure to Interface Monitoring"
Join @JuanAriel98, @umariomaker, and @jozer_eth.
⏰ 2:00 PM ET / 8:00 PM CET
👉nitter.cf/i/spaces/1wGWjjRdVZMKQ…
Jozer 🌴 retweeted
🧑🚀🌴 Next week, June 3 at 2:00 PM ET / 8:00 PM CET, we’re hosting an X Space with @ChainPatrol
🎙️ “From Infrastructure to Interface Monitoring.”
With:
@Juan_ChainPatrol
@umariomaker
@jozer_eth
We’ll discuss the importance of monitoring from multisig infrastructure to front-end interfaces as ecosystems scale.
See you there.
👉nitter.cf/i/spaces/1wGWjjR…
Jozer 🌴 retweeted
Hermes Agent as an Orchestrator and "open" vs "closed" specialist agents
ideally you want to be able to prompt:
> "fix the landing page"
> "build the lead magnet"
> "update the analytics"
> "turn this idea into a working tool"
> "check why the form is broken"
and have the right agent do the work.
that is why I like the Hermes + specialist agent setup.
Hermes becomes the command center, specialist agents do the execution
sometimes that specialist is Claude Code or Codex for coding tasks.
other times it is a research agent, SEO agent, creative agent, content agent, ops agent, or analytics agent.
the useful part is that you do not need one giant AI trying to do everything.
you can build a small team of specialists.
I call them vertical agents.
there are two types I run:
1. open specialists
flexible agents you talk to directly when the work is dynamic:
> a coding agent when you are building or debugging
> a creative agent when you are exploring directions
> a research agent when the question is still fuzzy
> a content agent when you want to jam on positioning, angles, or drafts
the workflow is not rigid. you go back and forth, steer, ask follow-ups, change direction. it feels more like working with a smart teammate.
2. end-to-end specialists ("closed")
agents for repeatable workflows. they do the same kind of job the same way every time:
> an SEO article workflow
> a weekly competitor research report
> a landing page QA pass
> a monthly analytics summary
> a content repurposing pipeline
> a lead list enrichment workflow
> a PR review or bug-fix workflow
these agents should have a dedicated model, dedicated context, and a clear process. they know the steps, the standards, and what "done" looks like. you can trigger them manually or schedule them as recurring tasks.
most open specialists eventually graduate into end-to-end specialists. you run them dynamically for a while, find the shape that works, then lock it in as a repeatable agent that runs the same way every time.
the mental model:
> you talk to Hermes
> Hermes routes the work
> specialists execute
> Hermes reports back
for marketers, this matters because marketing is becoming operational. it is no longer just campaigns and content calendars. it is landing pages, tracking, dashboards, research systems, SEO workflows, content engines, internal tools, conversion experiments, automations, and reporting loops.
imagine a place where context lives, where recurring workflows run, where you can talk directly to specialists when the work is messy, and trigger end-to-end agents when the work is repeatable.
the benefit of Hermes as the orchestrator: it does not have to be the one doing every task. it can be the layer that knows you, knows your workflows, and knows which specialist to call.
Jozer 🌴 retweeted
Check the Centaur repo, and please give us a star!
Feel free to open issues and PRs with questions, bug reports or feature requests.
github.com/paradigmxyz/centa…
Jozer 🌴 retweeted
Introducing deepsec, an open source coding security harness.
• CLI-first
• Sandbox-based scaling
• Pluggable coding agents
• Designed for large-scale repos
• Use AI Gateway or your own subscription
After months of successful internal use, we put it to the test on some of the largest open source codebases.
vercel.com/blog/introducing-…
Jozer 🌴 retweeted
Hypersig plans have been upgraded.
We’ve increased limits across Free, Starter, and Growth, giving Hyperliquid teams more transactions, wallets, sub-accounts, and agent wallets to manage execution together.
Live at hypersig.xyz
Jozer 🌴 retweeted
Look guys, it's actually really straightforward, a bunch of people staked their ETH on the Ethereum blockchain to earn yield, except they didn't want their capital to be locked up, so they actually staked with a liquid staking protocol called Lido who provided them a liquid staking receipt token called stETH, except they decided to juice their yield further by depositing their stETH receipt tokens into a restaking protocol called Eigenlayer, except they didn't want to lock up their capital, so they actually restaked with a liquid restaking protocol called KelpDAO who provided them with a liquid restaking receipt token called rsETH, except they decided to juice their yield further by depositing their rsETH tokens into a lending protocol called Aave so that they could open a leveraged looping position that borrows ETH against the rsETH collateral and restakes the ETH into rsETH which is then deposited as collateral, except it turns out rsETH used a cross-chain bridge called LayerZero that was hacked by north koreans causing rsETH to become undercollateralized and now these looping positions are stuck and unprofitable, and everyone is pointing fingers at each other, and also DeFi is a very serious industry
Jozer 🌴 retweeted
A new wave at Palmera 🌴🌊! We’ve updated our brand and website.
This is not a change in direction. It’s a clearer representation of how we operate.
Palmera supports chains with smart account deployments and the infrastructure required for ecosystems to operate with multisigs. The new site is designed to better communicate the scope, structure, and level of service we provide.
If you’re looking for a multisig provider, explore our services and book a call.
palmeradao.xyz/
Jozer 🌴 retweeted
Best GitHub repos for Claude code that will 10x your next project:
1. Superpowers
github.com/obra/superpowers
2. Awesome Claude Code
github.com/hesreallyhim/awes…
3. GSD (Get Shit Done)
github.com/gsd-build/get-shi…
4. Claude Mem
github.com/thedotmack/claude…
5. UI UX Pro Max
github.com/nextlevelbuilder/…
6. n8n-MCP
github.com/czlonkowski/n8n-m…
7. Obsidian Skills
github.com/kepano/obsidian-s…
8. LightRAG
github.com/hkuds/lightrag
9. Everything Claude Code
github.com/affaan-m/everythi…
Jozer 🌴 retweeted
Knowing true north.
I want to be direct about this.
The EF Mandate is a 180 from the direction the Foundation was heading under the recent leadership changes. A few months ago, the signal was clear -- lean into real-world adoption, support stablecoins, engage with institutions, help Ethereum win the race for relevance. Tomasz was brought in to operationalize that pivot. This document effectively undoes most of it.
Some key quotes that make the shift explicit:
"We are NOT Opportunists: We do not actively assist in adoption of Ethereum in ways that compromise trustlessness."
"We are NOT a Casino: We do not encourage people to take life-changing, and possibly life-wrecking, amounts of risk by going into personal debt hyper-gambling."
"Our priority, and the default path for decisions, in line with our mandate and the Only-EF Rule, is the CROPS-native approach."
"We leave space within the Foundation for the incrementalist approach only in tightly bounded circumstances."
"Right association also means we prefer to focus on individuals, teams, and projects that share our principles but operate in different domains, over those individuals, teams, and projects who are in crypto, but operate according to a very different set of standards."
Translation: the EF will deprioritize supporting stablecoin infrastructure, institutional onboarding, RWA tokenization, and broadly anything where the path to adoption runs through centralized intermediaries -- which is essentially everything that has product-market fit on Ethereum today.
This is a combination of d/acc philosophy and a broader leftward ideological pull within the EF. If you've been paying attention to the defense acceleration discourse, none of this is surprising. The framing is pure sanctuary tech -- Ethereum as digital refuge, not financial rails.
I respect the intellectual coherence. But the thing that strikes me most is the ability to hold two contradictory views simultaneously. The entire platform -- the treasury that funds the EF, the ecosystem that gives these words weight, the network effects that make Ethereum worth writing a 38-page manifesto about -- was built on financialization, speculation, DeFi, stablecoins, and yes, things with centralized access points.
Every application with real PMF on Ethereum today exists because someone made pragmatic compromises on the CROPS spectrum.
It was built by people who are willing to make compromises and see the world as it is, bringing product and people to Ethereum. The very people that this mandate is trying to alienate.
I will end with this quote from Lincoln: "A compass will point you true north from where you're standing, but it's got no advice about the swamps, deserts and chasms that you'll encounter along the way. If in pursuit of your destination, you plunge ahead heedless of obstacles, and achieve nothing more than to sink in a swamp -- what's the use of knowing true north?"
CROPS is true north. Nobody disputes that. The question was never the destination -- it was always whether you can get there without engaging the world as it actually is.
Jozer 🌴 retweeted
Claude Code skill files for smart contract auditing
@pashov: github.com/pashov/skills
@trailofbits: github.com/trailofbits/skill…
@cyfrin: github.com/Cyfrin/solskill
@0xkaden: github.com/kadenzipfel/scv-s…
@QuillAudits_AI: github.com/quillai-network/q…
@archethect: github.com/Archethect/sc-aud…
Did I miss any? 🧐
Jozer 🌴 retweeted
JUNE 2028.
The S&P is down 38% from its highs. Unemployment just printed 10.2%. Private credit is unraveling. Prime mortgages are cracking. AI didn’t disappoint. It exceeded every expectation.
What happened?
citriniresearch.com/p/2028gi…
Jozer 🌴 retweeted
Introducing EVMbench—a new benchmark that measures how well AI agents can detect, exploit, and patch high-severity smart contract vulnerabilities. openai.com/index/introducing…
Jozer 🌴 retweeted
🚨Claude Opus 4.6 wrote vulnerable code, leading to a smart contract exploit with $1.78M loss
cbETH asset's price was set to $1.12 instead of ~$2,200. The PRs of the project show commits were co-authored by Claude - Is this the first hack of vibe-coded Solidity code?
