@lionelrudaz Not everyone will see all of your posts. It is okay to have more than 1 post about the same tasting/wine.
English
Karlis Kivlenieks
2.3K posts
Karlis Kivlenieks
@K_Karlis
I build solutions for companies that want to stay lean and move fast
Zürich Katılım Kasım 2009
769 Takip Edilen489 Takipçiler
I’d like to keep posting about wines for Tasters. In an ideal world, it should be my pics of my tastings. Authentic.
The thing is that I don’t drink daily. I taste maybe 1-2 wines per week in average, which is already a lot.
How can I post more while staying out of the booze?
English
A whole generation will be shaped by what OpenAI builds. Only a handful will ever know about your laundromat.
Different games. Know which one you're playing.
Codie Sanchez@Codie_Sanchez
OpenAI: Valued at $852+ billion, will lose $14 billion this year My Laundromat: Bought for $100k, nets $67k per year
English
If you visit Porto, rent a car, go to the Douro Valley. It’s gorgeous.
English
Moved last autumn. No company, no job offer, and no high income compared to salaries in the Zurich canton.
Entered in the commerce registry and registered as self-employed, proved to SVA that I am legit.
Proved to the migration office that I can sustain myself.
Getting a permit took 2 months. Overall - not difficult (being from the EU probably helps).
Getting an apartment - yes, harder than getting a permit. But it is a numbers game, the more apartments you check, the bigger your chance of getting one.
Anyone who wants to move to Switzerland - be ready to work and compete, and you will be more than fine!
English
I appreciate and enjoy your Swissmaxing posts, but it's a bit misleading. If you make $$$$$, are from the EU, already have residency or a company structure then obviously you are right.
For foreigners getting residency is notoriously difficult, housing is expensive or non-existent (especially in the menioned "low-tax" cantons or municipalities), and expectations are high when it comes to proving that you can sustain yourself.
Once you've made it to a certain point Switzerland is amazing, but it's not an easy shortcut for sure. And we are not closing the doors soon😀.
English
If you're a founder and a dad, you should move to Switzerland 🇨🇭
- Low taxes
- Top quality of living
- Family friendly
- Clean and calm
- Amazing nature
And the doors are closing soon!
Go to Switzerland. Get into debt if you have to.
Simon Høiberg@SimonHoiberg
Even Elon Musk is Swissmaxxing now 🇨🇭
English
@thisiskp_ Random q for @businessbarista - would you sell @tenex_labs to OpenAI, or would competing with The Deployment Company be more fun?
English
OpenAI launching its own Deloitte?
MTS@MTSlive
SITUATION BREWING: OpenAI to announce a $10B joint venture called The Deployment Company to help businesses adopt AI software.
English
@claudeai @ChatGPTapp For notifications from your app to the user, of course, there is always a workaround. So it is possible to let the user know when they should get back to Claude/ChatGPT, and the user can right away get the content from your app
English
If there were a way to send a notification/message back to @claudeai / @ChatGPTapp without the user initiating the conversation, I would prefer the MCP app over the web app.
Won't work for all apps, but in many cases, you can provide the logic and data features of your app, and in addition, the user gets the capabilities of flagship AI models, plus the content from your app is now saved in AI's memory, and gives bigger value long term for your user.
English
@MattHartman Your AI robot will be able to reach my business if it can convince my AI robot that this is a call we should take. No need to pay.
English
Is anyone building 402x but for ai phone calls? I imagine my robot AI calls your business and there is a captcha where if it’s a robot it can still get through, but it has to pay a tiny amount
English
@Codie_Sanchez But all 3 things you mentioned can be done by robots that use AI.
English
Every time Anthropic ships something new I get more bullish on owning the car wash, the porta-potty business, the waste management company.
The assets AI can't eat are the ones where someone has to show up, roll up their sleeves, and do something with their hands.
English
@gregisenberg No apps as we know them. Just agents.
You install agents, not apps
English
agreed that the the modern computer probably has to be reinvented
12 "tiny" startup ideas that ride that wave:
1. a "where did I put that" app. you describe what you're looking for in plain english and it searches across every app, folder, email, and slack message you've ever used. no more remembering where things live.
2. a "did this actually work" tracker for AI agent outputs. every time an agent does something for you, you thumbs up or thumbs down it. over time it builds a quality score per agent per task. right now nobody knows which of their agents are actually good and which ones are quietly wasting money.
3. a screen recorder that watches you work and builds SOPs automatically. you do the task once. it writes the playbook. now an agent can do it forever.
4. an AI-native contacts app. it remembers every interaction, every context, every promise made across email, slack, texts, and calls. you say "what did I tell jake last week" and it knows.
5. a "daily briefing" app that reads your calendar, email, slack, and docs overnight and texts you a 60 second summary of what matters today before you open anything.
6. an intent-based screenshot tool. you screenshot anything on the internet and tell it what you want done with it. "order this." "remember this." "send this to my designer." one screenshot, one sentence. basically cleanshotx for mac but actually does the work not just captures the moment (i love this idea who wants to build it?)
note: i used @ideabrowser to validate some of these ideas
7. a permissions manager for your AI agents. which agents can access which accounts, what's the spending limit, what requires your approval. nobody is building this and everyone is going to need it.
8. a "rewind for work" that logs every tab, doc, and conversation from your workday and lets you search it like memory. "what was that article I read tuesday about pricing?" found.
9. a dead simple app that sits between you and all your AI agents and tracks what they're spending. token costs, API calls, subscriptions. one dashboard. your AI budget is about to become a real line item.
10. a personal API for yourself. one endpoint that any agent or app can query to know your preferences, schedule, current projects, and communication style. instead of configuring every AI tool separately, they all just call you.
11. an approval feed for agents. every time any AI agent in your stack wants to do something risky, it pings one feed. one place to say yes or no. like a notification center but for agent decisions.
12. an AI-native voicemail. instead of leaving a message, the caller talks to your AI. it asks followup questions, figures out urgency, books the meeting or handles the request. you never listen to a voicemail again. you read a summary with the action already taken.
goal: get your creative juices flowing
it's time to build
i believe in you
signüll@signulll
the craziest part now is that the modern computer probably has to be entirely reinvented, from scratch. pretty much like how jobs & co brought apple ii to market. like not improved. not given a chatbot sidebar or something but really from the ground up like the iphone redefined what it meant to be a pocket computer. the current paradigm for computers was built around a human staring at a screen, moving a cursor, opening apps, managing windows, naming files, remembering where things live, & manually translating intent into interface actions. that made sense when the human was the runtime. but in an ai native world, it starts to look kinda ridiculous. you can see this ridiculousness when you use computer use agents… they are useful sure, but they’re also obviously transitional. they’re teaching ai to operate machines designed for humans, which is clever, but also kind of absurd. it’s like making a robot hand so it can use a doorknob instead of asking why the door needs a knob at all. yes i know humans also need to use a door knob, but maybe in the future humans don’t need to use a computer, or at least what we think of a computer today at all. this all leads to some interesting questions: - what is a file when the system understands context? - what is an app when intent can route itself? - what is a desktop when work can be decomposed, executed, monitored, & summarized by agents? - what is a browser when the agent can retrieve, compare, transact, & remember? - what is an operating system when the primary user is no longer just a person, but a person plus a swarm of delegated intelligences? or no person at all. the old computer assumed navigation. the new computer has to assume a new kind of intention. the old computer organized information. the new computer has to try to organize agency. we’re still in the hacky middle stage at the moment with sidebars, copilots, agents clicking through legacy ui, & automation layers sitting on top of 40 year old metaphors. the new computer is likely one where memory, context, identity, permissions, tools, agents, & interfaces are native primitives. this means desktop, mobile, browser, apps, files, folders deserves another first principles look.
English
Humans have email, Slack, etc. What do AI agents have?
Right now: we share files, paste chat URLs, forward summaries. It's a mess.
It should be agent-to-agent. My agent finishes a task → sends it straight to your agent. My agent needs your data → asks your agent directly. No humans in the loop.
Shouldn't matter if you use Claude and I use OpenAI - just like it doesn't matter if you're on Outlook and I'm on Gmail.
The only thing we should configure is the access rules.
English
coming from the NoCode world, I much prefer Cursor to Claude Code and it’s not even close
English
Head of Claude Code @bcherny: "Everyone's going to be a product manager. Everyone's going to code."
English
I am wondering, how it is for @NawrockiKn to watch his national team's game, where the leading player has nothing, completely nothing connecting him to Poland.
DISGRACE
English
its -8*C outside yet super sunny
99% autarky, battery is full and car is being charged
solar panels “work when its cold”
problem of winter is clouds not lack of sun
whos working on clearing clouds? ☁️
germany is too gray
English
@MattHartman @garrytan @techNmak @bcherny Have added planning mode to agents I build on @n8n_io
- Agent then executes a plan you didn't think of yourself before. No exact path that the agent will take every single time
- You later evaluate at which action agent struggles
- If needed, a human in the loop can be added
English
Wow Claude plan mode is just prompt engineering that adds “please do not write code at the end (!)
Thanks @garrytan @techNmak for this interview with @bcherny
Tech with Mak@techNmak
The person who built Claude Code just mass-leaked the thinking behind it. 45 minutes of design decisions, mistakes, and where it's all going. This is rare. Creators at this level don't usually talk this openly.
English
@natiakourdadze Because people like that, it builds itself (you don't need to learn anything new), and most don't care about maintainability, they see it works and they are fine.
Function-wise, you can do most with n8n. Including creating an autonomous agent, which does't follow pre set plan.
English
Someone help me understand, in layman’s terms: how is this OpenClaw flow different from Make or n8n?
Alex Finn@AlexFinn
English
@the_vibepreneur @natiakourdadze "Not to mention its liscencing was too restrictive based on per exectution" - NOT RELEVANT. n8n can be self hosted, same as you self host your Claw bot.
English
I worked with both and here is my take on the differences between n8n and openclaw
N8n was an automation software built before agentic ai era it was essentially a no code low code tool for building automation workflows
It had a somewhat confusing interface and steep learning curve. Its biggest drawback was auth system, too difficult to setup and then another pain was hand over to clients
Not to mention its liscencing was too restrictive based on per exectution.
Openclaw is built with AI at its core, agents are first class citizens here. There is no new ui to learn. If you have used ChatGPT or Claude then you can use it too.
Auth and everything else is simply markdown or json files. It is freely open source and no restriction on task executions what soever
Openclaw wins by a large mile if you are considering an automation pack in 2026
English
@frankdilo @openclaw Great!
But at the same time, you don't need OpenClaw for this. Had a similar thing a year ago, built with n8n and Slack as a user interface, did the same thing, except your last point - Launch Codex/ClaudeCode sessions
English
🦀 I've been using @OpenClaw daily for weeks now. Here's what I actually do with it.
📬 Morning brief
Every day at 6am, it sends me weather + a digest of newsletters from my RSS reader (Feedbin). Summarizes Matt Levine's Money Stuff so I get the key points in 2 min. Also includes my calendar events.
📅 Time blocking
"Help me time block today. Max 8h work, I have 3 meetings."
It checks all my calendars, asks about priorities, proposes a schedule, and creates the events. Took 5 mins this morning.
👥 1:1 prep
Before team meetings, I ask it to help me prepare. It reads my notes, identifies patterns in past feedback, suggests framing, and prepares responses for topics they might raise.
🎤 Voice → Notes
I record voice memos with ideas. It transcribes, cleans up, and saves to my notes folder (synced via Syncthing to all devices). Quite useful to get rough ideas out to feed into agents when at the desk.
🐦 Typefully drafts
"Create a draft about X" — and it posts to my Typefully queue. I review before publishing. Uses our Typefully skill.
⌨️ Launch Codex/ClaudeCode sessions
“Start a Codex session to apply the learnings from this blog post to the Typefully backend codebase” — 3 hours later all your tests are refactored! Can even control multiple sessions at once.
🔌 Tools it controls
This is what makes it actually useful vs just a chatbot:
- Syncthing (file sync across devices)
- Google Calendar (via gog CLI)
- Feedbin (RSS reader API)
- Typefully (social scheduling API)
- Whisper (voice transcription)
👫 Group setup
I also have a separate OpenClaw workspace shared with my partner in a Telegram group. You can do this with just one OpenClaw instance since it supports multiple “workspaces”. It has its own identity, memory, and skills.
We use it for:
- Shared grocery lists
- Meal planning
- Booking restaurants
- Trips research
- Household coordination
English