If you’re reading this blog for urbanism, you’re probably already on Bluesky. If you’re reading it for tech, you’re probably not. This post is for the latter group; you are missing out! The short version is:

1. There’s a fun tech community on there these days
2. It’s radically open. With a little coding you can completely customize how you consume social media
3. There are some annoying people on there, but they are easy to avoid+block

If you tried Bluesky earlier and bounced off, or if you’ve just heard bad things, I think it’s worth reconsidering.

The short version

1. Start following my starter pack of interesting tech-related accounts
2. Subscribe to the For You feed. It is 1000% better at discovering interesting content than the default Discover feed
3. If you get annoyed by anyone, block or mute with abandon. More on that later.
4. When you’re ready, try making your own custom feed. Coding agents can make quick work of it, and using an LLM or System One model to filter posts works really well!

What you’ll find on Bluesky

There’s a fun tech community there (see: starter pack). It’s not as big as X but still has lots of big names (ex: Simon Willison, Martin Kleppman, Bryan Cantrill, Ethan Mollick).

It also has a lot of weird, small, accounts you can’t find anywhere else doing fun experiments with AI. Like Grace Kind’s unnaturally chipper Jev-based language model, or Cameron Pfiffer’s Void, or this bot which occasionally posts a banger:

people with robot girl pfps posting 'datacenters are destroying the planet' from their cyberpunk aesthetic accounts. bestie my culture is not your costume

— kira ☆ (@kira.ws) April 2, 2026 at 7:34 AM

My Custom Feed

I primarily consume Bluesky through a custom feed. It:

1. Takes every post from every account I follow
2. Runs it through an LLM scorer to eliminate posts I don’t want to see (topics I’m not interested in, ragebait)
3. Returns only the remaining posts

It’s a little Python web app that runs on my VPS, and the inference costs about $5/mo. It uses GPT-6 Luna and scores ~70k posts/month. I expect the price of capable inference to drop much further going forward.

This has been a big quality of life improvement for me. The media you consume shapes how you think+feel, and this lets me consciously choose what I consume. I don’t ever want to see rage-bait posts, and I don’t want my social media feeds to be dominated by US politics (I get enough of that on the real news). It also solves the age-old problem where you follow someone interesting and they post about a topic you don’t care about.

Here’s how I built it. Give that to a coding agent and it will easily build you a custom feed to your own specifications.

Blocking

It’s not all sunshine and roses. There are some annoying people on Bluesky (like any social network), but it’s easier to avoid them than you might think. Just block with abandon:

1. Subscribe to the AI Haters blocklist if you want to avoid extremely anti-AI people
2. If I see a particularly bad post, I use a script that blocks the author and everyone who liked the post. This is a nuclear option, but it works really well!

Ideally this wouldn’t be necessary at all, but there are some groups of people on Bluesky with no chill. I think it stems from:

1. The earliest Bluesky joiners are best described as Tumblr refugees, and they tend to be artists with an anti-AI bent
2. Subsequent waves of new joiners came from Twitter every time Elon did something horrible (including me), and so Bluesky ended up with a self-selected group of accounts who care a lot about politics.

Conclusion

Give it a try, I think you’ll like it! If you don’t like it after a few weeks, I’ll buy you a beer (offer valid only in Vancouver, BC).