ssp.sh

www.ssp.sh/brain/what-...

What I Learned throughout the Last Years Writing with AI ssp.sh

Added a dedicated note, as the idea is too big to bury in the AI writing note.

If You Start Writing Today, There's no way to Know if You Can Write without AI ssp.sh

If you can show you have written before using AI, people can trust you more easily than if you start today. If you haven't: > There's no way for readers to know if you can write without AI, whereas if you have written long enough, people know.

Writing with AI: What's the Best Approach? ssp.sh

Fifteen years of data engineering built Airflow, Dagster, Prefect and Kestra. This year we started building them again, for AI agents. For a while, new AI orchestrators appeared almost daily. www.ssp.sh/brain/are-w...

Are We Reinventing the Tools of Data Engineering for AI? ssp.sh

Find the full article at www.ssp.sh/brain/using-....

Keep AI Out of Your (Obsidian) Vault ssp.sh

I wrote a year back that skills are just notes for agents. IMO, this is still true; some are more sophisticated, some are less. But so can notes be with interlinked and related terms. Here's the note, just in case.

Skills: Evergreen Notes for Agents ssp.sh

Anything else that would be helpful to people reading my second brain, to get in flow with my constant updates? 🙂 Try it out at: 1. Recent updates: ssp.sh/brain/#recen... 2. Recent changes hover box with one box: ssp.sh/brain/will-a...

Will AI Replace Human Thinking? The Case for Writing and Coding Manually ssp.sh

Amazing talk about the Future of creativity with AI, it's a great follow-up to the TikTokification. My takeaway: > The goal of human art and craftsmanship is connection, not pure information. Humans take risks, doing something hard. The outcome will make you feel something. yo…

The future of creativity on the internet in a world with AI youtu.be

Currently, everyone on your team is running the same prompts locally on their laptop and syncing the shared artifacts manually, if at all. Max solution: Figma for Agents with a single shared canvas, with the whole team's agents running on it; no setup required. motherduck.com/…

Figma for Agents: How Airflow's Creator Coordinates AI ft. Maxime Beauchemin motherduck.com

www.ssp.sh/ai/ :)

AI Usage ssp.sh

Obviously, not every task requires a level-three agent with extensive setup and integrated tooling for extended data engineering. But the moment that output touches production, you want the deterministic core underneath it, not just a model that sounds confident. www.altimate.…

Where AI Agents Belong in Data Engineering: The Correctness Layer altimate.ai

Data engineering spent fifteen years building orchestrators — Airflow, Dagster, Prefect, Kestra. We are now doing the same thing for AI agents. Agor from Max the original creator of Airflow. Agent Teams from Anthropic, native to Claude Code. Omnigent from Databricks. Superset-sh, herdr, Gastown.

Automating my newsletter with the latest updates from my second brain, new essays, books I'm reading, notes, and latest social media post (pulled with DuckDB from Bluesky). No Gen-AI, all direct fetched from local MD files or Firehose via Python (linked), integrated with Listmonk and Neomd (email).

Writing code by hand might be dead, but the problem isn't AI code; it's that nobody knows anything anymore.

4 things I learned over the years with AI: 1. If consumed by a human, it should also be written by one 2. It's hard to finish an idea that's not yours 3. If you start writing today, there's no way to know if you can write without AI 4. AI won't replace human writing (as writing is thinking) You?

Is this how AI-scraping looks like? I got like ~4.5k total visits/h, 4-5 visits on each of my pages (notes & blogs). The source is unknown. 437 agents simultaneously on my `posts`, scraping every page? 🤔 I guess I need to ask the next versions of each LLM and see whether they use my knowledge.

In 2025, AI in data engineering was mostly slop on top of slop. The agents themselves are great. Almost every wrapper above them was not. For 2026, my prediction and hope is the same thing: less hype, more value. Stop putting AI in the name. Treat it as a tool, not the product.

It's so hard to finish an idea that is not yours (and suggested by AI). Some commented that it's also hard to finish an idea that is theirs—read the comments on HN now 😉.

How do you see the challenges of OSS in the age of AI? The video by ForrestPKnight triggered me to publish my notee. I have been a big fan of Open source for two decades, and that hasn't changed. I still think OSS is the right thing to do, if you can afford it. Love the framing as a gift.

I've asked myself where AI agents belong in data engineering work, specifically. Turns out there are 3 levels of "help" (chat, autonomous, dedicated tools)—but the real unlock is a 4th layer: a deterministic core underneath the LLM that proves correctness. Here's the breakdown.

Don't overrate how you do it; it matters more what you do, especially with LLM models. It's just a tool.