MDS specialize in Private LLM's and AI Data Center hardware. Tailor-made solutions using local data. Let's build your organization's AI future together.
Singapore
Joined October 2023
- Tweets421
- Following123
- Followers13
- Likes224
My Data Sys retweeted
This article turns your agent into AGI
Bookmark it or share it with your agent
nitter.gq/painn_x/status/2095060…
My Data Sys retweeted
I’m the actual human who made every single one of these videos they keep gluing together without asking. They love calling me ‘ex-Google engineer’ or ‘this guy’. Follow this guy and let’s actually chat. Original post is right here:
nitter.gq/shenseanchen/status/20…
Want the real AI Agent Harness System (Loop + Memory + Eval) instead of the mash-up? Grab my open-source Waku Agent (almost 1k stars): GitHub.com/shenseanchen/waku…
Original YouTube channel: yt.seanchen.io
(Better for your eyes. Trust me:))))
I also run a community where I host live biweekly Q&As and share all the original system-design files:
whop.com/sean-ai-community-d…
@X @elonmusk @benjitaylor @singhai @dinkin_flickaa please fix the theft on X.
@vattybear thanks so much for the constant support my friend! 🔥
THIS GUY MAKES COMPLEX AI AGENT CONCEPTS RIDICULOUSLY EASY TO UNDERSTAND.
No jargon wall. No assuming you already know what a reward model or an evaluation harness is.
Just a straight line from "I have no idea how agents actually work" to "oh, that's genuinely simple."
The best explainers do not simplify by cutting corners. They simplify by finding the one analogy that makes the whole thing click.
Our review of ISES 2026. mydatasys.com/articles/ises-… – at Kuala Lumpur City, Kuala Lumpur Federal Territory
Band aid, band aid, must be good for Malaysia, band aid, band aid. Some one else can do it and we will make the rules, blah blah blah. There is the problem. Expectations met.
At ISES today. Sustainable policies in Malaysia but my expectations are low. I am sure, therefore, they will be met. – at Kuala Lumpur City, Kuala Lumpur Federal Territory
My Data Sys retweeted
Someone cloned Netflix.
Then cloned Spotify.
Then cloned Instagram.
Then cloned Airbnb.
Then cloned WhatsApp.
Then cloned TikTok.
Then cloned Amazon.
Then put the source code for all of them on GitHub. For free.
Not one app. Not ten. Over 100 open source clones of the biggest apps on Earth. With source code. With demos. With tech stacks listed.
It is called Clone-Wars. 34,555 stars on GitHub.
Built by an Indian-origin developer named Gourav Goyal. He started collecting open source clones of popular apps into one list in December 2020. In March 2021, it went from 0 to 4,000+ stars in 7 days. It was on GitHub Trending for 5 days straight. Someone posted it to Hacker News and it hit #1 on the front page.
Here is what is inside.
Netflix clones. React, TMDB API, full streaming UI.
Spotify clones. Music player, playlists, search, albums.
Instagram clones. Feed, stories, likes, comments, DMs.
WhatsApp clones. Real-time messaging, read receipts, group chats.
Airbnb clones. Search, booking, maps, payments.
Amazon clones. Products, cart, checkout, Stripe payments.
TikTok clones. Short video feed, upload, likes.
Twitter clones. Feed, follow, tweet, retweet.
Slack clones. Channels, threads, real-time chat.
Trello clones. Boards, cards, drag and drop.
YouTube clones. Video player, search, comments.
And 90+ more.
Every clone has source code, a live demo, and the tech stack listed. React, Next.js, Node, Firebase, MongoDB, GraphQL, Tailwind. Every modern stack represented.
Here is why this matters.
Coding bootcamps charge $10,000 to $20,000 to teach you how to build apps like these.
Udemy courses charge $50 to $200 each. One app at a time. One framework at a time.
This repo gives you 100+ fully built apps with source code you can read, fork, and learn from. For $0.
Here is the wildest part.
The best way to learn to build Netflix is to look at someone who already built Netflix. Not a tutorial that teaches you one feature at a time. A complete, working clone with every feature connected.
You do not learn architecture from tutorials. You learn architecture from reading real projects.
100+ apps. 100+ demos. 100+ source codes. One repo.
Bootcamp: $10,000 to $20,000. Teaches 2 to 3 projects.
Udemy: $50 to $200 per course. One project each.
Clone-Wars: $0. 100+ projects. Every big app cloned.
34,555 stars. AGPL-3.0 licensed.
Every app you use. Cloned. Open sourced. Free to learn from.
(Link in the comments)
My Data Sys retweeted
This is really big news. Google introduced the Open Knowledge Format (OKF) - a standardized way to store information in a directory of markdown files. Makes it really easy to make a digital brain that agents can use.
These files can serve as a living wiki. You can give agents the ability to query them or edit them. They can interlink.
Seems to me this could replace Notion or Obsidian. I can think of so many uses for this.
Google's blog post: cloud.google.com/blog/produc…
An easier to understand explanation is the SPEC.md file:
github.com/GoogleCloudPlatfo…
I gave those two links to Antigravity and asked how we could use it for any of the projects we're working on. It came up with so many ideas. I would imagine Claude Fable 5 would whip up some pretty amazing things based on this system.
Currently creating an OKF library of our pepper garden. It's going to be a fun weekend.
When it's not your business you have no say.
🦔Microsoft canceled its internal Claude Code licenses this week after token-based billing made the cost untenable, even for a company with effectively infinite cloud resources. Uber's CTO sent an internal memo warning the company burned through its entire 2026 AI budget in just four months. American AI software prices have jumped 20% to 37%, and GitHub (owned by Microsoft) is dropping flat-rate plans for usage-based billing across its products.
My Take
The AI subsidy era is ending in real time. The same company that put $13 billion into OpenAI and built the Azure infrastructure powering most of Anthropic's compute just looked at the bill from a competitor's coding tool and decided it was not worth paying. That is not a productivity failure on Anthropic's end. Token-based pricing is forcing every enterprise customer to confront the actual cost of running these models at scale, and the number turns out to be far higher than the flat-rate experiments suggested.
This ties directly to my Gemini Flash post yesterday. Anthropic, OpenAI, and Google all raised effective prices in the last six months. Enterprises that built workflows assuming AI costs would keep falling are now watching annual budgets evaporate in months. Two outcomes look likely from here. Either enterprises scale back AI usage to fit budgets, which slows the revenue ramp the labs need to justify their valuations ahead of IPOs, or the labs cut prices and absorb the losses, which makes the unit economics worse at exactly the wrong moment. Both paths land in the same place, the numbers stop working, and somebody has to take the writedown.
Hedgie🤗
Gemini Pro tips
This Gemini update kills your biggest productivity leak.
And almost nobody is using it properly.
Here’s the workflow:
→ Turn on Workspace Intelligence
→ Use Gemini inside Chat (no tab switching)
→ Create a Project for each task
→ Run a long-running agent
→ Turn workflows into Skills
Now you’ve got:
Context → Automation → Output → Done
All in ONE system.
Save this video, you’ll cut your workload in half.
Want the SOP? DM me. 💬
Hermes Agent now has multi-agent via the Kanban
Hermes Agent Curator
Your AI agent has a dirty little secret.
The longer you use it, the dumber it gets.
Cluttered memory. Duplicate skills. Dead workflows pulling at the wrong time.
Nous Research just dropped Hermes Agent Curator and it fixes this for good.
A background agent that runs every 7 days while you sleep:
→ Grades every skill in your library
→ Merges duplicates into cleaner ones
→ Deletes dead weight automatically
→ Leaves you a report of what changed
You wake up Monday to a smarter agent. No babysitting required.
Save this thread, you'll thank yourself later.
Want the SOP? DM me.
Hermes Desktop
Hermes Desktop just made AI agents feel simple again.
And almost nobody is using this setup yet.
Here’s what the new free Hermes desktop app actually unlocks:
→ Manage multiple AI agents in one place
→ Switch model providers instantly
→ Add tools like browser search + CLI
→ Connect Telegram, Discord, email
→ Run local models for free workflows
→ Control memory, skills, sessions easily
This replaces messy terminal workflows with a clean dashboard.
Even non-technical users can set it up fast.
Save this video, you’ll set up Hermes Desktop in minutes.
Want the SOP? DM me. 💬
When you base your business on someone else's business there are always risks.
ANTHROPIC JUST BANNED A 110 PERSON COMPANY OVERNIGHT WITHOUT WARNING
monday morning at an agricultural tech company, every single employee wakes up to an email saying their claude account has been suspended
110 people locked out at the same time with zero warning and the email even pretended it was an individual ban with a link to a personal appeal form
it took them 10 minutes on slack to realize the entire org had been wiped at once.
not even the account admins were told it was coming
they submitted the appeal form and got no response, even after 36 hours later there was still nothing
AND it gets worse:
> their separate API account is still active and still billing them
> their admins can't log in to view usage or billing because the email addresses are banned
> they got hit with a renewal invoice the day AFTER the team account was suspended
> they have no idea what triggered it. fertilizer conversations? GPS satellites? agriculture in general?
so they're paying anthropic to get banned by anthropic while anthropic ignores their support tickets
the founder of the company laid out the bigger problem perfectly
banning an entire organization for one user's behavior means a single employee or careless intern can revoke claude access for your whole business.
there's no per seat guardrail, no admin override, no way to limit the ban radius
his words: "you have to ask yourself if this is a platform you can entrust your daily workflows to as a business"
every founder reading this who runs claude through their company should be checking right now what their actual exposure looks like
billion dollar AI company with zero enterprise customer support
A great Hermes guide
Want Hermes running in minutes?
Follow this exact setup flow:
1. Install Hermes from GitHub
2. Launch it inside your terminal
3. Connect Obsidian as memory source
4. Sync OMI for automatic knowledge capture
5. Activate dashboard mission control
6. Create skills for repeatable automations
7. Schedule background tasks daily
Now Hermes works like a teammate.
Not a chatbot.
Save this video, you’ll build your first AI agent system faster.
Want the SOP? DM me. 💬
OpenClaw vs Hermes
I tested Hermes and OpenClaw for hundreds of hours.
Here’s what actually happened:
OpenClaw broke mid-setup.
Hermes launched instantly.
Then I ran both together inside Telegram.
That changed everything.
Now my workflow looks like this:
→ Hermes supervises OpenClaw
→ Agents talk inside group chats
→ Tasks run in parallel
→ Sessions stay organized
→ Backups handled by Manis
→ Updates never stop progress
Winning move isn’t choosing sides.
It’s building an agent stack.
Save this video, you’ll avoid agent setup mistakes.
Want the SOP? DM me. 💬
My Data Sys retweeted
GOOGLE JUST MADE PRIVATE AI AGENTS COMPLETELY FREE WITH GEMMA 4.
Plug it into OpenClaw, run it on your own machine, and your AI stops being a chat window and starts acting like a real worker.
Local LLM's are the way forward.
𝗥𝘂𝗻 𝗚𝗼𝗼𝗴𝗹𝗲'𝘀 𝗚𝗲𝗺𝗺𝗮 𝟰 + 𝗢𝗽𝗲𝗻𝗖𝗹𝗮𝘄 𝗮𝘀 𝗮 𝗳𝗿𝗲𝗲 𝗽𝗿𝗶𝘃𝗮𝘁𝗲 𝗔𝗜 𝗮𝗴𝗲𝗻𝘁 𝗼𝗻 𝘆𝗼𝘂𝗿 𝗼𝘄𝗻 𝗺𝗮𝗰𝗵𝗶𝗻𝗲 𝗶𝗻 𝟯 𝘀𝘁𝗲𝗽𝘀.
No API bills. No usage limits. No subscription. Nothing leaves your computer.
Here's the full setup:
→ Step 1: Go to ollama.com. Download and install. Update to version 0.2.2.0 or higher.
→ Step 2: Open terminal. Type: ollama pull gemma4. Downloads the model. Done.
→ Step 3: Install OpenClaw. Select Ollama as your provider. Point it at port 11434. Pick Gemma 4.
That's it. Your AI agent is now running locally.
Message it through Telegram, Slack, Discord, or WhatsApp like a coworker.
Read files. Write code. Remember context across every conversation. All on your own hardware.
Gemma 4 ranked number 3 on the global open model leaderboard on launch day.
It beat models with 20 times more parameters.
The 26B version activates only 4B parameters at a time so you get near large-model quality at small-model speed.
Every AI subscription you're paying for right now could be replaced with this.