Jason Marshall retweeted
Replying to @F1
The guy who held the record for 16 years being the first to pass it on. That's class.
Jason Marshall retweeted
Grok Bot maxxing for marketers and GTM
We put everything we and our friends know into this one
SpaceXAI engineers just released a free 1-hour workshop on full Grok Bot Agents: best prompts → CEO bot → 15-25 agents → 100% automation from scratch:
0% → 5:56 - build your first Grok Bot
25% → 13:13 - ship 1 bot to 15 correctly and build CEO
50% → 30:00 - teach Bots to work 24/7
75% → 37:07 - secret skills of building teams of agents by GrokBot team
100% → 44:46 - full 24/7 system that automate your life
the real Grok Bot unlock isn’t better prompts - it’s turning one Bot into an always-on team that delegates work without you
watch the workshop, copy the team structure - then read the full Grok Bot architecture below ↓
I HAVEN’T GOOGLED A SINGLE THING THIS WEEK. CLAUDE BUILT ME A SECOND BRAIN THAT ALREADY KNOWS EVERYTHING
I pointed Claude Code at an Obsidian vault and told it to build Karpathy’s wiki idea
went to sleep
woke up with three folders, a CLAUDE.md that runs the whole system, and a living wiki that links everything I’ve ever read
now I drop any article, transcript, or PDF into one folder and say “ingest this”
claude reads it, links it, files it, connects it to everything else
my friends are still copy-pasting into ChatGPT and losing context every conversation
the only thing separating us is one setup:
claude code + obsidian + 5 minutes
every source captured. every connection mapped. zero knowledge lost
if this is the setup you’ve been looking for
like & bookmark so you don’t lose it
Jason Marshall retweeted
APPLE JUST SHOWED HOW TO RUN 10 AI AGENTS LOCALLY ON MAC - NO CLOUD, NO API KEYS, ZERO COSTS
00:10 Apple engineer says: "your data stays on your device, AI available anywhere at any time, zero usage costs"
agent reads your code, checks GitHub, finds what needs attention and writes a report - all on your Mac, nothing goes to the internet
10 agents work simultaneously - one writes code, another tests, third fixes bugs - parallel with no queue
built a full iPad app from scratch in 2 minutes, fixed its own mistakes and compiled without issues
takes 5 minutes to set up - and you never pay again for a bot that runs 24/7
Jason Marshall retweeted
I genuinely don't understand why everyone isn't using this yet
Andrej Karpathy, a co-founder of OpenAI, posted a simple idea that hit 16 million views: stop using AI to write code, use it to build a second brain.
You point Claude Code at a folder, drop in any source, an article, a transcript, a PDF, and Claude reads it, links it, and files it into a living wiki of everything you know. It compounds like interest, the more you feed it, the smarter it gets.
Here's the whole thing:
> Install Obsidian, create a vault, open it in Claude Code
> Paste Karpathy's wiki idea file and tell Claude to build it
> Claude makes three folders: raw for sources, wiki for its pages, a CLAUDE.md that runs it
> Drop any source into raw and say "ingest this"
> Ask questions across everything, forever
Five minutes to set up, and you never start from a blank chat again.
Full step-by-step guide with Claude and Obsidian, link below.
Bookmark this
Jason Marshall retweeted
THIS SITE COST AROUND $12 IN CREDITS TO BUILD. STUDIOS QUOTE $35,000 FOR THE SAME THING.
What's on screen isn't a basic landing page.
It's a fully animated, scroll-driven site, generated end to end in one agentic session with Claude Code + Higgsfield.
What's actually on the page:
→ Cinematic motion clips pulled from 30+ generative models
→ Scroll animations written automatically - zero hand-coded keyframes
→ 6 cinematic effects baked in with no config: film grain, particles, vignette, glass cards, color tints, scroll pacing
Scroll the demo and one question won't go away: did Claude really assemble all of this in a single pass?
For boutique studios billing $100-149/hr, that question lands like a verdict.
What it normally takes:
→ A designer, a motion artist, and a developer
→ Weeks of handoffs between them
→ 6 systems wired by hand - GSAP ScrollTrigger, Lenis smooth-scroll, frame extraction, asset optimization, layout, copy
That pipeline was the moat. It's what justified the invoice.
Here's the part studios and their clients won't enjoy hearing.
The price gap:
→ Boutique agency build: $6,000-$35,000+
→ Industry average project: ~$5,280
→ Delivery cost: a Claude subscription + a few dollars of Higgsfield credits
→ Timeline: weeks of production → a single session
One operator can now run all six systems in one pass and ship a working site - without touching a frame extractor or writing a CSS keyframe by hand.
Full breakdown of how it's built in the article below.
Save it & read today 👇
Jason Marshall retweeted
I Turned Claude Code Into My Business's Second Brain
In this video:
- How to build a 2nd brain + operating system for your own business
- Which tools I have it connected to to speed up my workflows
- How to stay provider-independent (Codex etc)
- How to set it up for a team environment
Full breakdown:





































