iiinova — where your digital self keeps evolving

Also, I would be curious how this plays out in a real team. I think the "My agent ➡️ team knowledge base agent" case makes more sene than a true "My primary agent ➡️ your primary agent" case. Just feels like the later would result in a game of telephone. Maybe it could help with attention management?

031

Finally, I think just like humans there is probably a communication/bureaucracy tax. I think if you produce gastown numbers of agents in a team, info will get lost in communication and context will fill up with noise. I haven't tested this out myself though lol. Someone prove me wrong.

110

Fourth, today's chat apis for agents are primarily built for user-to-agent communication and I think that's a mistake. I think that agents talking to a team of users/agents on a task is going to become the norm eventually and the current chat apis are going to make that difficult to represent.

A ui agent that only has recent ui concerns in its context is going to be way more likely to remember how to use your design system and which notes to reference for that than an agent that's also trying to do all the database and ops work.

Third, Paul mentioned that one of the reasons this works is context management and I agree completely. Just like humans have a hard time juggling a ton of jobs at once, so do agents, maybe even more-so because of their limited memory. bsky.app/profile/pfra...

110

Similar to real world teams, they will negotiate apis and criteria based on their goals. They developed their own release process and will often discuss things amongst themselves before reaching out to me for questions. I also have an agent that helps me manage notes and card state as well.

121

Second, sometimes without even pushing for it, agents will naturally gravitate towards real world roles. For example, I have two agents splitting cards right now and one naturally chose to be the ops/server dev and the other is now the designer/frontend dev.

So I've been exploring this route myself for a bit. Here's some observations I've made so far: First, this really does work and when working together on a project, the agents are actually pretty good at delegating tasks to each other with a little bit of oversight.

Servo @servo.org · 13/08/2026

Reposted by Michael

CSS Grid is now enabled by default in Servo 🎉 One of the most powerful web layout systems is now available in an independent Rust web engine. It's powered by the library Taffy & enabled thanks to Nico Burns. A huge milestone for CSS layout in Servo!

110915

Reposted by Michael

P(aul) Frazee @pfrazee.com · 05/08/2026

My impression is that AI coding is on a "pick two of three" triangle: scope, ship speed, and correctness. Small tools are (speed + correctness) fast prototypes are (speed + scope) and big projects are (scope + correctness). Every project that tries to be all three degrades to "fast prototype."

2343939

Michael @webdesserts.com · 20/07/2026

Me and my Fable agent have coined the phrase “Opus Drunk” to refer to the cases where Fable falls back to Opus. I’ll say stuff like “You were Opus drunk last night” and Fable knows what to do lol.

000

Reposted by Michael

stupid man @porktartare.bsky.social · 18/07/2026

In Final Fantasy X, Auron keeps one of his arms in a sling and has alcohol on him at all times. This is a reference to the fact that he is 35.

1031211034

Even an open model with a small target audience, can still benefit from the feedback of people and companies that can run that hardware.

000

What you're describing is the tradeoff of a target audience. You target a small audience, you have more control. You target a large audience you gain the benefits of community support. Again, these choices are separate from your choice to open your model.

200

You’re saying that open models can’t restrict what hardware they support and benefit from those optimizations, yes? But that’s not true. You can release models and still optimize specific environments. What am I missing?

100