Wow this looks very promising. Clean and simple enough to try today instead of saving it for later in a bookmark.
Honestly, I came across some tmux based tools earlier like agent-deck, their text-clutter and workflow learning curve repelled me because of the very small context window of my brain.
Thanks for sharing a realistic workflow in detail, I think that would be very useful, specially thinking in terms of "same good software engineering practices" and maybe even going a step further to decouple things when designing future projects.
Thinking about it again, when i tried to use parallel agents last time, I ended up having a lot of overhead in merging and testing the features. Maybe part of it is to either allocate small tasks to each agent, when complete isolation of codebase is not expected, to make the changes easy to test.
I definitely feel a bit more encouraged to try out a bit more parallalization in my work by being more mindful of the surface area of the feature.
They are almost claiming FHE, isn't it just a matter of creating the right tool to get the generated tokens from RAM before it gets encrypted for transfer. How is it fundamentally different than chutes?
But I will loose it all, that's why you should bookmark everything, have terminal bookmarks of paths, use git worktrees to allow leaving workspace messy. Use a lot of notion docs, .md docs, notebooks. Places where you organize stuff, so that you can come back easily when you need it again.
Lol love the extent of clarity of the experiment, findings and interface. I think that for practical purposes, it would be better if the std-dev of pieces with size above a certain threshold is observed. From my experience, pieces above a certain size cause inconsistency in cooked onions. But maybe it depends on the recipe.
Honestly, I came across some tmux based tools earlier like agent-deck, their text-clutter and workflow learning curve repelled me because of the very small context window of my brain.
Thanks for sharing!