• Steve Ruiz: https://x.com/steveruizok | https://www.linkedin.com/in/steve-ruiz-61a150239/

• Marc (host): https://x.com/marchattonhere | https://www.linkedin.com/in/marchatton/

Links

• TLDraw: https://tldraw.com

• TLDraw SDK: https://tldraw.dev

• Make Real: https://makereal.tldraw.com

• TLDraw Computer: https://computer.tldraw.com

• TLDraw on GitHub: https://github.com/tldraw/tldraw

Ben Guo explains the next computer is a personal cloud: software-company-grade infrastructure for personal computing, not just for businesses.

In this episode he demos Zo live and shows what that looks like when files, automations, memory, hosting and model access live in one persistent system you own. Personal computing is starting to feel like the early PC movement again, and the early days of the internet and P2P file sharing/hosting.

Watch on YouTube

• 00:00 Ben Guo, Zo and why personal computing is back

• 04:03 The personal cloud thesis

• 06:27 Zo demo starts: files, automations and hosting

• 09:19 Data imports as memory

• 12:31 Persistent, elastic compute

• 14:24 AI provider API keys and integrations

• 16:11 Q&A: privacy and ownership

• 17:47 Q&A: product taste and velocity coding

Zo is hiring cracked engineers

https://www.zo.computer/careers

Follow / get in touch

• Ben Guo (co-founder): https://x.com/0thernet or https://www.linkedin.com/in/0thernet/

• Rob Cheung (co-founder): https://x.com/perceptnet

• Marc (host): https://x.com/marchattonhere or https://www.linkedin.com/in/marchatton/

Products/tools mentioned

• Zo Computer: https://www.zo.computer/

• Claude Code

• OpenClaw: https://github.com/openclaw/openclaw

• 23andMe: https://www.23andme.com/

• ClinVar: https://www.ncbi.nlm.nih.gov/clinvar/

Companies mentioned

• Venmo: https://venmo.com/

• Substack: https://substack.com/

• AWS: https://aws.amazon.com/

• Vercel: https://vercel.com/

• Cloudflare: https://www.cloudflare.com/

• Hetzner: https://www.hetzner.com/

I feel equally terrified and equally excited about the rise of LLMs.

After hitting the weekly limits for codex 5.3 on the $200, I was shitting my pants whilst being hooked as 13 year old me playing Age of Empires. It is hands down the most powerful coding model. It unlocks long running agents and the concept of Code Factories.

What seems unthinkable is suddenly acceptable the next week!!!

A few weeks ago, I read this article by about the Overton window https://ghuntley.com/overton/

Think right wing vs left wing politics. Why do you think something is acceptable whilst another person not?

Human psychology extends to new technological shifts. NEVER BEFORE has the rate of change and disruption to tech work been this fast.

This is a great mental model and learning. In this world your goal should be to move new ideas through your own mental model from:
unthinkable → radical → acceptable

That’s it for today.

Cheers friends :)

Here’s a snippet of Ryan providing an overview of his Code Factory setup:

You'll find this more fun watching episode (instead of listening), here it is on YouTube:

Bye for now.

Maybe you find this useful :)

A) Weird shit is happening, and its going to get weirder

• Steam, steel and infinite minds: Every era is shaped by its miracle material. Steel forged the Gilded Age. Semiconductors switched on the Digital Age. Now AI has arrived as infinite minds. Ivan Zhou (Notion CEO)

• Karpathy feeling behind, plus the ripple. The sands are shifting, Karpathy feels like he’ fallen behind (link)

• “AI will kill all the lawyers” (Spectator). A sobering read. “Last week we did an experiment, a kind of simulation. We took a real, recent and important case – a complex civil court appeal which I wrote, and it took me a day and a half. We redacted all identifying details, for anonymity and confidentiality, and we fed the same case to Grok Heavy AI. And then we asked it to do what I did. After some prompting, the end result was…’ He shakes his head. ‘Spectacular. Actually staggering. It did it in 30 seconds, and it was much better than mine. And remember, I am very good at this.”

B) Building with core AI

• LLMs under the hood: A BEAUTIFUL video showing how conceptually work. OMG it’s stunning. Welch Labs YouTube

  

• “You’re suddenly knee deep in chunking…” A pragmatic “ship something real fast” thread, aimed at avoiding infrastructure rabbit holes. X (formerly Twitter)

• State of agentic iOS engineering in 2026. A snapshot of how mobile dev workflows are mutating. And dev workflows in general. Dimillian

• Clémentine Fourrier: LLM Evaluation Guidebook v2. Good reminder that evals are the steering wheel, not an afterthought ngntipkolamrenang.twstalker.com

• Continual system prompt learning for code agents. People are starting to treat prompts like evolving infrastructure. X (formerly Twitter)

• tldraw: the fairies (agents) are amazing. Multi-agent coordination is a ‘fun’ puzzle to solve. X (formerly Twitter)

C) Greater productivity with AI

• How to prompt your Claude Code to keep it going from your phone (with VPN etc) granda.org+1

• React Grab CLI: Click in the UI, comment and automatically changes will be implemented agentically. Aiden Bai

• Prototyping isn’t thinking. debbiewidjaja.com

• Amp: thread maps. Clever feature to navigate your AI coding chats (in Amp). X (formerly Twitter)

<the end. enjoy your coffee, or matcha, or organic freeze thingy whatever>

p.s. Soz for being a couple weeks late. Holidays + sick children + sick wife + sick me.

Opinion

• Essay: The 2 problems of online consumption of AI generated content at scale: Signal erosion and verification difficulty. AND what you can do to counter them.

• Vertical AI is where it’s at: The next big wins are in narrow domains where data, workflows and evals are all specific and painful.

• Intro to LLMs: Karpathy’s talk still the best starting point. Here is a useful summary.

• “Thought does not require language. Language is an expression of thought. Intelligence requires thought more than language” - Yann Le Cunn

Productivity

• Compound engineering plug-in by Kieran Klaasen. With each feature you build, the plug-in: #Engineering

1. Documents patterns for the next feature

2. Creates reusable components that accelerate future work

3. Establishes conventions that reduce decision fatigue

4. Codifies knowledge that compounds across the team

• try out Claude Code’s frontend-design-skill to build UI without the purple gradients :D #FrontEnd

• n8n’s team built a Figma plugin that reads CSS tokens from Git and updates Figma variables in one click. No third party token tool, just their own automation #Design

• BugBot from Cursor is a low effort way to auto review PRs. Similar to Charlie and Codex review automations.

Novel use cases

• Clawdbot on X: Personal productivity bot by steipete. Powered by his duct-taped build of Warelay -- a CLI for sending/receiving WhatsApp via Twilio or WhatsApp Web.

• LLM audits as a service: Anthropic testing smart contract vulnerabilities - preliminary showing $4.6M in funds at risk with a PoC.

Evals

• Deep dive on LLM evals in The Pragmatic Engineer. Stop what you’re doing right now and read this!

  • p.s. I took the Maven course by Hamel and Shreya and cant recommend it highly enough!

Dan Shipper dropped a thought provoking yet seemingly obvious post.

My first reaction: yes.

Second: If cost of code will trend towards zero, what actually changes based on where the value sits.

Third: what can we learn from the past?

Caveat. This might age as well as fresh bread from the lovely local bakery, not a Meerlust Rubicon (top tier red wine). Genuinely curious to re-visit this post in 10 years time (reminder set!).

Here goes…

Abundance

LLMs will make code creation cheap, trending towards zero. But it will not make software worthless.

When code get cheap, the act of keyboard punching is no longer the bottleneck. I hear you, software engineering is more than that (I know!)

The way we design, integrate and earn trust with that code changes.

Most importantly scarcity moves upstream: attention and trust.

Subscribe now

History tells a story

Printing press

Suddenly pamphlets, religious texts, you name it, were in abundance.

Books with beautiful bindings and signed copies. These became more premium.

Clothing

Fast fashion makes it trivial to own clothing. But top quality suits, your Gucci’s of the world etc still demand a hefty premium.

Side note: my wife hates fast fashion and is a pure cotton maximalist.

Entertainment

Music and video streaming drove the marginal price of music to zero. But live shows and concerts still demand a premium. Immersive experiences you could say.

Ok, so what is this abundance premium for software?

Dan is right: LLMs change how software is built. LLMs make it easy to spit out simple CRUD, auth, pricing integrations, all of that jazz. One person with an AI copilot can ship what used to take a team.

But the hard parts are harder than ever:

• Building a trusted brand people will bet their reputation on (buyers)

• Getting the mind share of human beings (this is going to get 10X worse in the future)

• Workflows, not apps: Deeply integrating into the direct context of the users.

• Solving compliance problems. This is why companies like Wise and Deel have such a huge moat.

Only a handful of companies can achieve all those things meaningfully.

Humans are still humans: Enter the abundance premium

Code creation is in abundance. So the average product is better AND cheaper. And creativity soars as software is democratised.

But the really hard parts about creating a business/product that wins are going to get even harder. To stand out, you have to solve:

• Brand: Narrative, trust and distribution

• Workflows: Meet users at their context and solve compliance

• Taste: Delight by default not exception

So that humans still want to hear from you.

The best people to solve those problems are going to be even more in demand and demand more of a premium.

And products built by those people will still demand a premium, cause they got the hard parts right.

Here’s the first weekly wrap of news. Happy bookmarking for later (that you won’t ever end up reading).

Opinion pieces

• Shipping is marketing, prioritising, building, testing and more. Practice shipping

• ProductTalk – “AI Changes Everything (And Nothing At All)”. The real AI skill for PMs is not prompting, it is resisting the urge to skip discovery just because shipping is cheap.

Novel designs

• Fast (sync) vs background (async) agents. Cursor’s Composer model is perfect for in the flow AI pair programming. GPT 5.1 Codex is perfect for delegated work

• Code heatmaps: Giving devs a bird’s eye map before they touch a file is quietly a 10x experience for onboarding and refactors.

• AI coming home to Sheets/Excel: Ramp Labs (yes the neobank) and Claude making moving into the tools finance and ops people already live in.

Deep dives

• Lessons from 6 months of using Claude Code to refactor 300k lines of code

• Vercel: “What we learned building agents”. The sweet spot of low-cognitive, high-repetition tasks.

• How Figma built human-centric AI evals for Figma Make, including design and functionality scoring.

“It’s easy to over-engineer your eval stack, your data set, some part of the quality loop — but it all depends on what users want to use your product for…. Building conviction on where you want to invest is the key part to get right.”

Learning

• LangGraphEssentials: Short course teaching LangGraph concepts like nodes, edges and state for building graph-style agents in Typescript.

• A quick start guide to MastraAI (LLM framework for Typescript). Get started in 5 minutes