i made my macbook's notch actually do stuff. music, my calendar, a shelf for files, and when claude code wants to run a command it asks me up there instead of in the terminal. about a week in. it's called brimlight
@cory_schulz_@zack_overflow Games are the best proof of it. Years of a free 3D canvas and the menus still ended up as flat lists and grids, because reading and finding things is just faster that way
@zack_overflow Relayout yes, but then its a different layout every time. People find things by where they were last time, so if the agent moves stuff around on every resize you lose your place. Constraints are what keep it the same
@zack_overflow Free placement is fun until the window changes size. Constraints are what keep it working on a screen nobody designed for. The bigger change is where the agent shows up, not how its boxes are laid out
@ashxhart Checking before load is the right call. The nastier version of that bug is a model that loads fine and gives quietly wrong output, so a quick known-answer prompt right after load catches the rest
@nntaleb Shows up in engineering first as no junior hiring. The catch is seniors come from juniors, so the bill arrives in five years when theres nobody to promote
@leopardracer Finding seven is the cheap part. The work is triage. Ask it for a repro per finding, a request that actually leaks the data. The ones it cant reproduce are usually the false positives, and the access control one is the first to check by hand
@Crypto_Moe84 What fades is checking, not typing. Anyone can let the model write it. The people who stay sharp still read the diff and keep one test the model didnt write. Thats the part worth doing by hand
@Kalshi Allowed once is a weak number. A blanket yes says little about trust, the better one is how often people undo a purchase. Id want limits per amount and per merchant that the agent cant raise on its own, with a confirm above them
@Zeneca Open prompts like this give you a confident list of generic ideas. Make it tag every suggestion with the file or number it came from, and drop anything that cant point at one. Whats left is the useful part
@twannl@sendable Redraws are the ones a profiler never volunteers. Quickest check without Instruments is to leave the app idle and watch CPU. If it isnt flat at zero something keeps invalidating, then you know where to point Instruments
@StatsWire Total token volume going up doesnt say much about your own limit, more people are using it too. The number that does is tokens per 1% of your weekly limit, per model. Track that on your own sessions and you can see if Opus costs more of the plan or you just use it more
@naaiyy_ Start with idle. Whatever it costs when nothing is happening gets paid all day, so i measure that first. Running sample on the pid for a few seconds shows where the time actually goes
@adriankuleszo Most of your fixes swap decoration for the real thing. Dots and a globe say security in general, the padlock and the named files show what the client actually gets. Claude goes generic when it doesnt know what the real objects are
@hany99dev Whats the part that made it stick this time? For terminal people its usually whether several sessions are easy to watch at once, and whether a permission prompt can sit unseen in another window
@Voxyz_ai Okay scanning the logs beats guessing. The other half is a limit you can see while you work. A number you only check after you hit it cant change the habit that burned it
@Mr_Buzzoni The reason helps for the case you didnt write the rule for. A bare rule only holds for the exact situation you had in mind, a reason lets it make the same call in the next one