"His life was plagued with notoriety. He was in court in one of his numerous lawsuits when the bailiff held out the Bible and asked him his name. He responded, Frank Lloyd Wright, world's greatest architect. When he returned home, his wife Olgivanna said, Frank, the man was simply asking your name. He replied, but I was under oath."

> The worktree system removed the friction of context-switching - juggling multiple streams of work without them colliding.

I'm so conflicted about this. On the one hand I love the buzz of feeling so productive and working on many different threads. On the other hand my brain gets so fried, and I think this is a big contributor.

I would like some research regarding multi agent flows and impact on speed and correctness, because I have a feeling that it's like a texting and driving situation, where self perception of skill loss and measured skill loss diverge.

I have nothing to back up the idea though.

Ooooh very interesting idea.

I also have nothing to back it up, but it fits my mental models. When juggling multiple things as humans, it eats up your context window (working memory). After a long day, your coherence degrades and your context window needs flushing (sleeping) and you need to start a new session (new day, or post-nap afternoon).

you do lose context, but if you generate a plan beforehand and save it, then it makes it easier to gain that context when you come back. I've been able to get out things a lot more quickly this way, because instead of "working" that day, I'll just review the work that's been queued up and focus on it one at a time, so I'm still the bottle neck but it has allowed me to move more quickly at times

I am just running multiple agents to work on different projects. Once in a while I have a feature that splits nicely into multiple threads that can be developed concurrently, and I use several concurrent agents to do it. But that is rare.

Is constant juggling of multiple agents productive? I haven't seen the allure (except maybe with 2 agents sometimes). I guess it depends on what kind of tasks one is doing and I can imagine it working if doing large, long-running tasks, but then reviewing those large changes and refactoring becomes more difficult. And if you're juggling multiple agents, there's the mental context switching and tooling overhead for managing them. Maybe predictable and repetitive tasks can work well.

I prefer focusing mostly on 1 task at a time (sometimes 2 for a short time, or asking other agent some questions simultaneously) and doing the task in chunks so it doesn't take much time until you have something to review. Then I review it, maybe ask for some refactoring and let it continue to the next step (maybe let it continue a bit before finishing review if feeling confident about the code). It's easier to review smaller self-contained chunks and easier to refer to code and tell AI what needs changing because of fewer amount of relevant lines.

I have two modes. Mostly what you describe (phase 1), but followed by "project management" (phase 2), where I iterate through the impementing the plan done in phase 1.

the way I handle this is that I just create pull requests (tell the agent to do it at the end), and then I'll come back at a later time to review, so I always have stuff queued up to review.

I do parallel agents in worktrees and I don't always constantly keep an eye on them like a fry cook flipping 20 burgers at once. Sometimes it's just nice to know that I can spin one up, come back tomorrow, and some progress has been made without breaking my current flow.

I'm building Vivino, but for Chocolate bars. App is called Chof, currently in test phase, and submitting for app store approval this week. Scanning, saving, rating bars that you find.

I got to a pretty stable scanning flow using Gemini 3 flash.

Walking, and Writing on Substack

Currently; > Main goals: Improving my writing and finding some people with similar interests Writing about my current walking season that I'm in, combined with reflections during the walking, recently about walking around the island of Menorca, and Aloneness:

>> https://felipevanbeetz.substack.com/p/build-some-capacity-to...

Thinking about starting another Substack: > Main goal: Audience growth Called something like: "Walk more", "Walk intentionally", "Move intentionally", "How to walk more" About: Short, (bi)Weekly, Practical tips/inspiration, to Move (and specifically Walk) more and more intentionally.

I'm super curious about how far Dexcom and Abbott's research departments are with developing these technologies. It could be a (partial) disruption for them.

Also - flashback to Rockley Photonics ($RKLY) - and their years-long promise of non-invasive glucose monitoring.

"Dumb electronics" will be hot - iPods/MP3players, dumbphones, e-ink screens/phones/readers, film cameras.

"Dumb electronics" - iPods/MP3players, dumbphones, e-ink screens/phones/readers, film cameras.

I just bought a Lootoo PAW6K after getting fed up with the iPhone and the headphone plug adapter.

This player has its own OS, no WiFi or only for firmware upgrades. Has no apps and boots up under three seconds and large capacity from SD Card. The best is it just plays.

What's even cooler is that it's a DAC so I can have my headphones plugged in to it and then use Spotify/Service to stream to the player.

Expensive though at $1000 but just how I want it. My headphones decoupled from my mobile phone.

Diva, you can get an iPod nano on eBay…

I'm currently working in an iPod Nano like device based on LicheeRV Nano, TP4057, 2.8" Touch screen and a 1200mah battery. Software is buildroot and lvgl.

Not so serious ATM but looks promising so far.

Unfortunately all official sipeed 3" touch displays are sold out, probably i need to go I2C or DPI...

I didn't want an iPod nano, as I'm wanting to break away from the grey corporate gardens.