switching to copy on write worktrees is the biggest game changer it should become common knowledge pretty soon and it's already available on most operating systems
You also need a deduplication, because with simple copy on write you will have a copy for writing the same - change a byte in a file, get a copy, then change it back, get a duplicate.
Deduplication in ZFS needs 5G of RAM for 1TB of logical data - if you expect your agents to produce 2TB of data, you should provide 10G of RAM for deduplication.
Why are your agents expected to produce 2TB of data? Not criticizing, I'm curious. Outside of classifiers I don't have any of my agents produce data, they produce scripts to produce data so it can be deterministic
Any substantial work on substantial software project can give you that. It is often the case with C++ that some logic resides in header files included by most of the project. If you change that logic, you have to rebuild your project and you will get mostly the same object and/or executable files for most of source code, but still slightly different [1].
Tons of screenshots to check for visual bugs - they have a tendency to run smoke tests and benchmarks for everything - and as tokens get cheaper it's easier to fan out more and more subagents that set up their own environment etc. if you want to get the capabilities you're paying for out of them you have to let them run in a loop hill climbing until everything works. But if you don't invest in specifically supporting the agentsby building a good dev environment for them - sure they're good enough to unblock themselves but whatever they do is going to be chock full of slop (like the crashpad reports...). And they won't clean up after themselves. Partly because dumber models and smart models hitting a stupid spike will clean up after themselves by wiping your dev server and breaking all the other sessions that unblocked themselves in chaotic ways, partly because you might have updated permissions/instructions after a previous rather annoying experience like that to strictly ban commands that delete files and containers and stuff. I was running into my machine crashing after hundreds of gigs of storage space were consistently being eaten up over a day and it was all slop. Dead worktrees, "smoke tests," dead docker containers, dead anonymous volumes, files full of screenshots, playwright screen recordings at way too high a resolution, clones of a dev DB, saved logs, etc. a lot of that was fixed by a couple instructions in a markdown file telling the agents to not be stupid about that but a lot of the rest requires actually investing in the agent's dev environment so like they can run their own independent server without doing some ad hoc nonsense that leaves behind yet another random docker volume
thanks to the parent you're replying to, I discovered there's numerous projects that try to retrofit CoW into worktrees + also fill in the gaps for mostly-shared data like build artifacts! I've decided to take lane (https://github.com/lukeed/lane) for a spin as I type to see how it goes.
At least the fans will allow for really short breaking distances.
I historically argued for a sort of horror-vehicle that would achieve autonomous driving "early" by exploiting downforce from powerful fans, but I mostly imagined it being used for autonomous deliveries and never imagined there being people inside it.
idk about the safety of involving jumping cars into car crashes, I'd still prefer the brakes (obviously not always enough time). The one useful situation I could see is if you're driving (accidentally I hope) off a cliff.
And how many people can be like that guy?
Our jobs are part of an industrial process(literally). We get money performing a business function within a larger organisation.
I'm a pretty clever guy, a high achiever, yet at my very best, at my absolute peak efficiency I probably can do the job of 5-50 mediocre people.
And there are millions of people smarter, better and faster than me.
And most of them have more money.
reply