Founder @agenticracy — open standard for responsible human-AI co-working. Psychologist. NHS AI lead. Built the contract the field needs. https://xitter.cf/t.co/7joBk3BFNu
London, England
Joined March 2010
- Tweets6.3K
- Following5K
- Followers1.5K
- Likes6.6K
Vlad I🔁🌈 retweeted
Hermes command cheat sheet. Save this. You’ll probably need it again.
UPDATED for the current Hermes command set, including a bunch of genuinely useful commands that have landed recently:
• /goal
• /loop
• /heartbeat
• /bg
• /btw
• /plan
• /review
• /refine
• /moa
• /busy
The commands are spread across Desktop, CLI, messaging, and the terminal, so I rebuilt the sheet around what you’re actually trying to do.
Sessions & context.
Active work.
Goals, loops & plans.
Models & behavior.
Skills, memory & tools.
Automation & coordination.
Recovery & troubleshooting.
Plus the Messaging/Gateway and Terminal essentials.
Verified against the current Hermes source today.
Bookmark it and keep it around.
Vlad I🔁🌈 retweeted
Home Information maps manuals, maintenance records, and device controls to a visual floor plan to organize your property data spatially.
github.com/cassandra/home-in…
Vlad I🔁🌈 retweeted
Recommended paper for agent skill builders.
There are 56,804 public agent skills today, all competing for fewer than 100 reliable trigger slots in the system prompt. Your own playbooks compete for that same space, and the long tail never gets used.
skills separates the three things installation bundles together. Content, persistence, and automatic triggering. Only triggering needs to sit in the prompt.
A path addresses any skill, subtree, or collection, and reading it is enough to use it. A directory becomes a menu, so bundles stop being all-or-nothing. Vendoring copies a skill into your Git tree at the same path, so your team owns and adapts it.
No manifest, no lockfile, no registration, and SKILL.md is unchanged.
Paper: arxiv.org/abs/2608.12610
Track more trending AI papers in our academy: academy.dair.ai/
Vlad I🔁🌈 retweeted
New Preprint 🚨 In Favour of Personalised AI Moral Advisors: Six Design Conditions researchgate.net/publication…
Vlad I🔁🌈 retweeted
Attackers have frontier AI. Defenders need a frontier AI ecosystem—the best open and closed models, force-multiplied by a global community.
During the Hugging Face incident, closed AI blocked essential forensics. An open-weight frontier model helped contain the intrusion.
That’s why we created the Open Secure AI Alliance.
AI security advances when the industry builds in the open, together.
We're introducing the Open Secure AI Alliance with industry leaders to develop new techniques and tools to safeguard software and agents.
By sharing models, tooling and research in the open, we can broaden the community of defenders.
Learn more about the founding members’ contributions: nvda.ws/4pD8Fc5
ALT Logos of various companies including Adobe, Cisco, and Microsoft.
Vlad I🔁🌈 retweeted
Curated list of agentic AI projects and papers for medical imaging, electronic health records, and drug discovery
github.com/AgenticHealthAI/A…
Vlad I🔁🌈 retweeted
Contractor assessed its own service in ICB procurement ift.tt/tWNlfoi
Vlad I🔁🌈 retweeted
New market map: AI assistants in iMessage 📱
The next major interface for consumer AI? Text messages.
People don’t want to open an app every time they need help - they want a contact they can text like a friend.
My roundup of the assistants + infra providers below 👇
Vlad I🔁🌈 retweeted
// Self-Harness: Harnesses That Improve Themselves //
(bookmark this one)
Most of the agent scaffolds we rely on today are built once and remain frozen or mostly unchanged.
The harness, like the skills, needs to evolve with new models.
What if the scaffold rewrites itself?
This new work treats the harness, the prompts, tools, and control flow around the model as a learnable artifact that improves from its own runs rather than staying a fixed wrapper you hand-maintain.
The scaffolding becomes the part that compounds, run after run. If you run long-horizon agents, a self-modifying harness turns scaffold upkeep from manual work into something the system earns on its own.
Paper: arxiv.org/abs/2606.09498
Learn to build effective AI agents in our academy: academy.dair.ai/
Vlad I🔁🌈 retweeted
New paper on how AI agents are reshaping knowledge work.
This is a nice economic read on where agents actually change knowledge work to meet that gap directly.
(bookmark it)
It studies agent adoption across three dimensions: autonomy, efficiency, and the scope of tasks workers hand off.
The friction people keep hitting with agents is rarely model quality. It is that almost nobody has been taught how to work this way.
Paper: arxiv.org/abs/2606.07489
Learn to build effective AI agents in our academy: academy.dair.ai/
Vlad I🔁🌈 retweeted
"My most daily used agent is running off a Raspberry Pi which is at least two or three years old; all that it has is 8GB of RAM. You see my point about accessibility, personalisation, relevance, use. [...] This is my point: the barriers have fallen." 🫶
Singapore's Minister for Foreign Affairs, Dr Vivian Balakrishnan, built his own agentic AI tool running on a Raspberry Pi (inc appropriate security measures!)
"You cannot govern a technology you have only been briefed on."
Singapore Minister for Foreign Affairs, Dr. @VivianBala, echoing @karpathy and @yacineMTB on why he runs NanoClaw: "you can outsource memory and computation, but you cannot outsource your understanding"
xitter.cf/VivianBala/status/2055…
He also shared his tech stack for running his second brain for Singapore's Foreign Affairs Ministry and parliamentary affairs:
- @AnthropicAI Claude Agent SDK
- Baileys + WhatsApp
- Mnemon (Graph Memory)
- @ollama + @nomic_ai
- @ggerganov Whisper.cpp + OneCLI
With special notes on how he handles security and isolation, and what implications he sees for Singapore Inc.
Vlad I🔁🌈 retweeted
The questions concerning AI, employment, meaning of labor, human capital, and our role in society are some of the most important questions of our time. As always, Daniel is writing about these topics in a very thought-provoking way.
Vlad I🔁🌈 retweeted
Zo Community Build Hours today! 👇
come build with @zocomputer today! no slides, no long talks. bring something you're actually stuck on and we'll work through it live together.
Vlad I🔁🌈 retweeted
AngelList introduced USVC: venture investing for non-accredited investors starting at $500. Hear why Jason thinks the social media criticisms lack merit and says: "More liquidity for investors is always a good thing. Let a thousand flowers bloom.”
Plus:
💰 Was the NYT wrong to host a discussion about “micro-looting”?
🪖 A Special Forces soldier was insider trading on Polymarket… does it matter who he bet on?
💵 Why rich families teach their kids about finance but public schools don’t.
It’s a TWiST Saturday special!
0:00 Intro
1:18 Naval's $500 VC Fund Explained
5:54 Should You Trust Critics With 2K Followers?
7:21 Learn By Betting — Jason's Philosophy
10:10 Northwest Registered Agent - Get more when you start your business with Northwest. In 10 clicks and 10 minutes, you can form your company and walk away with a real business identity — Learn more at northwestregisteredagent.com…
12:30 The Maduro Polymarket Scandal
13:28 Should the Military Bet on Missions?
19:55 LinkedIn Jobs - Hire right, the first time. Post your first job and get $100 off towards your job post at LinkedIn.com/twist
29:32 NYT Defends Theft & "Social Murder"
30:28 There Is No Moral Equivalence
33:41 The Nepo Baby Behind the Article
35:42 Prof G's "Resist & Unsubscribe" Movement
37:54 Walk The Walk — Hasan, Bernie & Performative Outrage
44:49 Teaching Kids About Money
48:21 The Rich Get Richer & The Poor Stay Poor
49:31 Outro
cc: @Jason, @Lons, @AngelList, @Naval, @Polymarket, @nytimes
🎥 Watch the full episode here 👇
Vlad I🔁🌈 retweeted
Great explanation of what AIUC-1 is and why you should avoid it.
Well worth a watch.
