Rudy Sabich retweeted
Jev + GrokBot is the best AI agent system I’ve built in my life
It just made my setup CHEAPER and FASTER than what 95% of people are running...
setup takes literally 7 minutes:
prompt → GrokBot → Jev decision → GrokBot execution → result
step 1 → open @typesafeai , create API key (keep it off chat paste)
step 2 → tell Grok Bot: store TYPESAFE_API_KEY in the secure field
step 3 → prompt Grok Bot: install typesafe-sdk on Agent Computer + smoke system_one (Choice)
step 4 → tell Grok Bot: build the usage lab (router, dry-run, config, logs) - or clone Github below
step 5 → add skill jev-usage-router: before browser / research / retry / extra bot → call the router, honor action
step 6 → stay shadow first, read logs, then active when you trust it - kill switch: bypass jev or enabled: false
step 7 → flip active: GrokBot obeys route - Jev decides - GrokBot executes - humans control irreversible actions
the result: Jev + GrokBot the best and fastest agent running directly on your computer rn, I’ve already tested it on routine tasks - and the results are genuinely incredible
You can come up with endless ways to use Jev + GrokBot - but the most important thing is to install it as soon as possible
Copy this 2028 setup, explore my repo below - then read the full Jev deep dive ↓
Rudy Sabich retweeted
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI?
I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev
• 20-200x faster
• 40-400x cheaper (w/ output tokens free)
• Frontier composable intelligence optimized for decisions
AFAICT the shortest path to AI-based economic revolution
Rudy Sabich retweeted
SpaceXAI engineer (ex. Cursor):
"right now I'm running 10-20 GrokBot agents that automate 90% of my routine
i have a Chief of staff agent. he knows about all my other bots and manages everything"
in a 30-minute podcast, a SpaceXAI engineer showed how to build a team of GrokBot agents that will work for you 24/7
Worth more than a $500 course on agentic engineering
Watch today, then read how to build a Grok agents team from scratch in article below
Rudy Sabich retweeted
Super excited to lead a workshop on Grok Bot next Thursday (8/20) at 9 AM PST showing just how nimble and powerful this tool is!
Sign up here: luma.com/38zzy3ov
Rudy Sabich retweeted
30 YEARS. WORST AUCTION DAY EVER!
After 30 years in the auction industry, I’ve lived through recessions, the GFC and COVID. But today feels different.
Two weeks in a row, zero registered bidders at auction, even after positive inflation news.
It’s a reminder that confidence, not just interest rates, is what drives property markets.
When buyers disappear, that’s a signal we can’t ignore.
#marketwrap #realestate #australianrealestatemarket #propertymarket
Rudy Sabich retweeted
Note to self:
Don’t invest in property in Melbourne.
I can only guess who built it…
Rudy Sabich retweeted
Grok just made one of its smartest moves yet.
It's no longer trapped inside a chatbot.
Now it works directly inside Google Docs, Sheets, and Slides.
That changes a lot for anyone creating content.
Rudy Sabich retweeted
Melbourne Australia has turned into a third world disaster.
Importing trades from third worlds has got to be one of the stupidest decisions government has ever made.
This house would be worth probably $750 000 (1.7 million with interest) this is what you get.
You cannot hate mass migration enough. Politicians involved in mass migration should be jailed and deported.
Rudy Sabich retweeted
Run Kimi K3 on a Mac Studio 🫰
K3 is 2.8T parameters and 1.6TB on disk, which makes it impossible to run on Apple Silicon.
Until now.
Our MLX port is now open source: github.com/PipeNetwork/kimi-…
To accomplish this, we solved two things:
1. We wrote a streaming converter that walks one layer at a time, so that mlx_lm doesn't need to materialize the whole model.
2. REAP pruning sits on top and scores all 896 experts against a calibration corpus to keep only ones your workload needs.
That's what brings K3 down to 350GB and inside a Mac Studio.
Releasing the model weights and technical report of Kimi K3.
Kimi K3 is our most capable model: a 2.8T MoE model with native visual understanding and a 1M-token context window.
New model architecture: 2.5x the intelligence per unit of compute, not just more params.
Alongside Kimi K3, we're opening up more of the stack behind it — high-performance attention kernels, MoE communication library, and infrastructure for running agent environments at scale.
Model weights: huggingface.co/moonshotai/Ki…
Tech report: github.com/MoonshotAI/Kimi-K…
Tech blog: kimi.com/blog/kimi-k3
Rudy Sabich retweeted
REVEALED: Here Are the Mainstream Journalists on China’s Payroll 🚨
I exclusively uncovered the identities of prominent U.S. journalists flown to China by a CCP-linked influence operation seeking “favorable coverage” and “positive messages” about Beijing. 🧵
Rudy Sabich retweeted
Thank you! I take this very seriously.
There is a window of opportunity to make generational wealth right now by following the right people and making the right high conviction trades.
Both the market and X has incredible alpha right now and who knows how long it will
last.
I said it in the podcast, but if I had one skill, it would be to digest incredible amounts of content, connect the dots, and separate the signal from the noise.
The way I post and teach is to show people how my brain works in realtime so that they can train their own tendie tingles too.
The engagement bait is just for fun.
Honestly, great interview by @kevinxu.
I really enjoyed it, and whether you agree with him or not, I think he's spot on about how the world of finance has shifted toward X.
He does a great job explaining the bigger picture: Wall Street increasingly uses this platform for idea generation and due diligence because many of the sharpest investors, analysts, operators, and builders are actively sharing insights here in real time.
Rudy Sabich retweeted
I created a handbook to help you learn AI agents.
It gives you:
• Must-know AI GitHub repos.
• Free courses to master AI agents.
• Papers to understand AI fundamentals.
• Curated videos to learn AI agent foundations.
• Books to get started with AI agent engineering.
• Condensed guides to broaden your AI agent knowledge.
(24 HOURS ONLY!!!)
To get it for free:
1 Follow @systemdesignone [MUST]
2 Like & Retweet to get DM
3 Reply "Handbook"
Then I'll DM you the details.
