@dickson_tsai@noahzweben this, also workflows should not be treated as static scripts that you build once, but more like model itself that you constantly improve, an example is the pr review workflow I built in our startup that reviews itself recursively or when given false positives from its reviews
@orca_build 100% this! Can you add the same for worktrees? Bonus points for allowing changing the background color, pattern or even an AI generated image, please! That would immensely help with switching between contexts
@OnlyTerp did it get stuck at some point or is it just a simple sequential multistep one with no parallelization? What was the token count for that run?
Today, we're launching shift. We're starting by cleaning your apartment in New York City, for free.
Here's how it works. Book a shift cleaning. A vetted shift operator comes to your home wearing one of our devices. They clean. They leave. You pay nothing.
In exchange, we record the cleaning. Robotics is being built on data about how people do daily tasks, and the value of that recording is what funds the service. Anything personal in it is anonymized before the recording is processed.
By now, you have heard about the shift to AI more times than you can count. About the shift toward you, the part where you actually feel it, you have heard almost nothing. Shift is what starts to make it concrete, in specific cities, with specific services.
Today, cleaning in New York. Soon, handymen, repairs, and errands across the globe. And this is just one side of shift, with more on the way.
Comment โshiftโ and weโll send you an early access link.
@mattpocockuk test behaviour not implementation. it's not seam count, it's seam placement: put seams at boundaries only (component, page in storybook, endpoint, BE logic, infra) and treat inside each as black box. many boundaries is fine. pain comes from seams at single functions or mocking
@InsiderPresider@orca_build asked Claude to spin up an individual subagents to explore the features of each, then create a categorized list of variables to compare against, create a comparison table and lastly render it in HTML with monospaced vibes
@maddada@luke_aus@orca_build I use ubuntu 26, if you are not afraid of going deep into maintaining cross language rpcs then tuari, electron otherwise, thereโs nothing wrong with it ๐ Iโll def check out your tool!
@maddada@luke_aus@orca_build to make claude code write to other tabs running other claude code sessions (multi agent orchestartion), read from tabs with streaming logs or browser tabs
@maddada@luke_aus@orca_build Awesome stuff, @maddada! The deal breakers for me were Linux support, seamless iOS pairing, and first-class memory management. Literally none of the other tools came even close to Orca in that