dSebastien

I created an AI skill for this a while ago: https://www.dsebastien.net/garmin-ai-skill/

Same. Also reminds me of similar apps I used heavily and all of it vanished with the rise of streaming platforms

I built ghradar.dsebastien.net recently because I needed something like that

Yes there definitely are.

I created a custom status line to see/track everything I need: https://github.com/dsebastien/claude-epic-status-line

That avoids surprises

Counting things

IMHO understanding terms and concepts matters more than ever

We should watermark everything we create, AI-generated or not. This might shield our content from being stolen moving forward

You can create those manually but if you want to enforce those then you need the subscription

Yes and they have a specific subscription for managing sandbox policies across the enterprise: Docker AI Governance

The one thing I wonder about is how you enforce the usage of Docker Sandboxes vs running the agent on the host directly, apart from scanning machines for binaries

Add me there

Certainly not perfect build we wrote this spec for the National Bank of Belgium a few years ago. Served us well.

https://github.com/NationalBankBelgium/REST-API-Design-Guide...

True :)

I agree with the spatial memory and the many possible and valid ways to approach reading and learning. But it's much harder to recall, connect and leverage ideas that way

Better yet, take actual notes abd give yourself space to think: https://www.dsebastien.net/2022-02-17-how-to-capture-book-no...

Obsidian + Markdown + YAML frontmatter turns knowledge bases into operating systems.

You can really build anything on top of Obsidian. And when you combine the power of the Web platform exposed by Obsidian and its API with properties and Obsidian Bases, you can have tons of fun.

At least I'm having tons of fun.. ;-)

Hope Omarchy will make that a default:)

I miss Joel's blog posts!

I've created about 20 Obsidian plugins, little tools, websites, a new storefront, etc

https://tools.dsebastien.net/

I guess it makes sense since we as humans tend to be far less inclined to help someone who is not polite/is not friendly, so that "bias" is part of the training data, thus influences how LLMs function

This is a HUGE improvement to the status quo. Give it some time. They do care

Check out my article: https://www.dsebastien.net/the-must-have-obsidian-plugins-fo...

Fully agree with you

Context Management for teams deserves more attention. I'm focused on this at work. Some of that will be covered in my upcoming videos

Same, very cool DX. A Markdown report of issues would be nice to have though to save a few tokens ^^

I printed blog posts for 15 years. I used to print everything I wanted to read during my train commutes. I learned so much that way :)

I'll check it out, thanks!

I wish I kept my demo files!

Knowii, a community for knowledge workers who want to excel and thrive. We explore the frontier of knowledge management, personal organization, zen productivity, clarity, personal development, project management... And AI

https://dsebastien.net/community

I've been using Simplewall on Windows for a while but I think it's not maintained anymore. Need to find an alternative