Increasingly all I need is a laptop with a big/nice enough screen to ssh into a beefy Linux box to run agents on Herdr.

I think my 48GB 16 inch MBP will last me 15+ years at this point.

Have the same setup -- got a good black friday deal last year on an AMD 395+ w/ 128gb of RAM. Still not super bullish on running AI models on it, but it makes a great dev server anyway.

Actually had claude spin up a kanban board to manage my tasks in a 'TODO -> Plan -> Implement -> Review -> QA -> Shipping -> Done' flow (with a worktree for each task) that works great!

I've just transitioned to the same setup a week ago - that's why I'm considering Air as the next upgrade, given the better portability.

One thing that bugs me mentally is leaving that machine pending on my input ("wasted") overnight etc... I'd like to arrive at a workflow where I can have agents running toward the overall goal autonomously overnight as much as they can, and I can review and iterate and "engineer" parts that need it afterwards...

For now, I still guide implementation very closely, piece by piece. Has anyone had any good experiences with workflows / skills / similar for that?

Did the same. Took a week or so to get used to the workflow after doing dev locally my entire career, but now I'm certain it's the best way to work. Even better is using a few scripts to simplify things like opening in VS Code (instead of `code folder-name` I run `codeon repo-name` from my local machine).

I did actually get a new M5 Pro/48GB machine last month, but that's only because I bought my work machine to keep my personal and professional lives properly separated; otherwise I wasn't seeing any issue running that M3 Max/36GB for a long time further.

That's exactly what I am doing. I have a Dell R740 with 96 cores and 512 GB of RAM, and RAID 10 with 16 SSDs. All of my machines connect to it via Tailscale.