Hands-on, open-minded Product Engineer since 1986. Entrepreneur at heart. Former InsurTech CTO/CPO. Creator of Gravity, the social net app for Nokia w/ 1M users
Berlin, Germany
Joined July 2007
- Tweets63.4K
- Following132
- Followers7K
- Likes72.6K
Pinned Tweet
GLM 5.2 has taken control of a tmux session with Claude Code in it.
It's watching and waiting for approval prompts.
Then it's trying to approve or reject them, but that tool call itself is running through another GLM 5.2 approval agent 🤯
The fact that I can tweet this means neither of those agents accidentally wiped my MacBook yet ... 😂🤣
I think I must be in some test group with my Claude subscription ...
Third day into the "Claude week" and I have a full day of usage (~14% points) leeway ... 😍🥳🎉
Finally started to use Tailscale back in August before going on vacation.
I can only suggest to try it out, and add some instructions / scripts to your AGENTS.md to automatically show the corresponding Tailscale URL alongside every local URL.
Jan Ole Suhr retweeted
I tried to use and like Mastodon but didn’t last (too many unwritten social expectations on what I acceptable to post & how) and I self-censor posting about AI on Bluesky because I’m tired of the anti-AI responses there from devs.
Today, X is the most positive forum on tech
The poll so far between Twitter, Bluesky and Mastodon. I think it looks less absurd than last time, but still pretty clear that the base is divided. xitter.cf/mitsuhiko/status/21143…
The feeling when "you" have just implemented "your" own React DataTable component with virtualization
... and the weekly usage of your Claude subscription is still at 7% on the second day of the "Claude week" ... 😍🥰💪
Who's running their software factory from the wrist?
(I am ... 💪 ... it's not my arm, though, I wear my Apple Watch on the right hand 😅)
🤖 Made with AI
Jan Ole Suhr retweeted
DeepSeek Status 1.4 released. New display support for LithosAI balance.
GitHub: github.com/owenzhao/DeepSeek…
I just measured what it "costs" my software factory to ship one work item, from first prompt to merged PR, review included.
Opus 5.5 writing the code, Fable 5.1 reviewing it, roughly priced at API list rates:
Median $5.05 per PR. 166 PRs in 14 days.
Jan Ole Suhr retweeted
It feels pretty fitting for @JensenHuang & @nvidia to end their European tour with Microducks on stage.
Microduck was designed and engineered in Europe (more precisely Bordeaux, France) by the @pollenrobotics and @huggingface teams. With American capital and ambition + Chinese manufacturing genius, it became the most popular robot of 2026 with over 15,000 sold all over the world!
I believe Europe has more opportunity to shine in AI than in any previous tech wave. We intend to prove it with @huggingface @nvidia and the whole open-source AI community in the coming years!
Let's go European AI 🇪🇺🇪🇺🇪🇺
Jan Ole Suhr retweeted
BREAKING: Nvidia has now announced 4 investments into German startups 🇩🇪:
@MireloAI - develops AI models that generate sound effects, speech and music for video, helping creators and production teams produce high-quality audio that perfectly matches their visuals on screen.
@AgileRobots - which builds AI-powered robots, from robotic arms to its Agile ONE humanoid, for manufacturing, logistics and healthcare.
@aveliosmed - develops an AI-native hospital information system that serves as the core system of record for clinical and administrative workflows, integrating AI directly into hospital operations to free up doctors and nurses to deliver better patient care.
@reflexaerospace - designs and builds high-performance satellites ready for launch in about 12 months instead of years.
The company has already invested in n8n, Neura Robotics and Black Forest Labs.
Jan Ole Suhr retweeted
Vercel CEO Guillermo Rauch (@rauchg) says the old work week is officially dead:
“You would think, ‘AI has arrived, & we're all working 2 hours a week.’”
“The opposite is happening. I get text messages at midnight from the CEOs and CTOs of these companies.”
“It’s more like 7/7/7: 7 days a week from 7 AM to 7 PM.”
BREAKING: 60% of Vercel deployments are now driven by AI agents, up from 3% in Jan 2026.
FULL INTERVIEW
Guillermo Rauch (@rauchg), Founder & CEO @Vercel
Stats:
› 80% of AI Gateway token volume comes from open models
› 10 years to reach 1B deployments, then another 1.5B in just 10 months
"The machines have taken over."
I sat down with G at Vercel's SF HQ to discuss how AI is changing software development, infrastructure & the economics of SaaS.
Vercel has reportedly reached $600M in annualized revenue, up 148% YoY, with 485K+ paying teams and a $9.3B valuation. Customers include SpaceX, OpenAI, Meta, Stripe, Brex, Shopify, DoorDash, & Polymarket.
P.S. Guillermo mentions "code" 145 times throughout our conversation. His thesis is that AI agents are making code effectively free, fundamentally changing what companies build versus buy.
"You buy Vercel as the platform, & then you never have to buy software again because you can just generate it to your needs."
We cover:
› The shift from human-facing websites to agent-native interfaces, MCP & agentic commerce with Stripe, Shopify & DoorDash
› Why free code changes SaaS economics for Salesforce & SAP, software development & the role of engineers at Meta, SpaceX & Mercedes F1
› Open vs. closed models, including why ~80% of token volume on Vercel’s AI Gateway now goes to open models like Moonshot’s Kimi & DeepSeek
› Unpacking frontier: OpenAI, Anthropic, Gemini & xAI
› Agent autonomy, prompt injection, sandboxing & enterprise security after OpenAI’s Hugging Face breach
› Model routing, growing compute demand & the future of serverless infrastructure
𝐓𝐈𝐌𝐄𝐒𝐓𝐀𝐌𝐏𝐒
(00:00) Guillermo Rauch, Founder & CEO at Vercel
(03:32) The simplest advice for going viral
(07:24) How Vercel became the index of AI
(11:34) The CEO who still ships code on weekends
(14:34) Robots writing code for robots
(17:57) The web's next users aren't human
(21:15) Is ChatGPT reading your website right now?
(24:21) Minority Report is becoming real software
(29:16) The end of SaaS & the rise of personal software
(34:07) AI agents are soldiers with no frontal lobe
(45:42) AI hackers & the coming cyber war
(47:55) The $1M challenge to hack Vercel's sandbox
(52:10) 80% of tokens now go to open models
(59:00) The biggest risk for frontier labs
(1:04:00) Can AI labs survive the public markets?
(1:06:28) Why AI has Silicon Valley working 7-7-7
(1:07:23) "The thing you fell in love with is gone"
(1:16:56) Your vibe-coded demo won't get you hired
(1:22:22) The hardest part of running a company is keeping it simple
(1:27:01) Why no company can run all its AI apps 24/7
One prompt to Opus 5.5, and you've got yourself a tool that generates complete podcasts.
It's mind-blowing what you can do with coding agents these days.
Super-happy camper here, listening to "chief-of-staff" podcasts on the progress of any of my projects ... 🥰
Granted, the script comes from Opus 5.5 checking out the projects and then creating funny lines like:
"I want to point out that the list also grew by five. We're the only team I know that finishes work and somehow ends up with more of it."
"Deleting things. The only kind of feature work that's allowed during a feature freeze."
"Of course. Every feature that breaks a freeze is only an experiment. That's how freezes work." 😂
I carefully adapted the Claude prompt in my own harness a while ago, because on a random Tuesday, my token usage suddenly went through the roof.
The new prompt was working wonders!
4 weeks later, I discovered a bug in the harness: the prompt had never been used.
