> If there are 10x and 0.1x engineers, you bet there are 10x and 0.1x doctors.
This is a false equivalency, as the 10x engineer is measured differently than a great doctor. A 10x doctor in your analogy should mean "this doctor is least likely to kill you during surgery", or "is better at following checklists".
The "best" doctors I've met have off the charts systems analysis skills, and they were in all kinds of specializations. Human physiology can be quite counter intuitive at times, and great doctors have great observability skills.
I bought a cheapo lifetime pass in the early days of plex. Their business leadership decided to make Plex more like a TV than a personal media server, and the UI / UX changes reflected this.
I got a great deal as an early user, but new users have Good Reasons not to use plex anymore.
I just set up my pipeline to do this exact thing for both the Apple and Android ecosystems, dispatching loads to my mac studio or Linux box accordingly. I moved the runners off GitHub because uptime for GitHub actions has been trash lately, and the Apple Silicon runners are pricey.
Claude was great at figuring out what was broken when and either fixing it, or clicking as far as it could until it needed me.
You could say I'm mostly just IRL hands for the AI now.
There is a reason why VMs even are a thing at all: they can offer better security guarantees than alternatives.
A separate user is a good start but LLM tests themselves show they can cleverly bypass guardrails if they figure out they are in a sandboxed environment of some kind, right?
So, I read those test results as: an LLM is less likely to do something crazy if it thinks it has the whole environment to itself.
It is great and currently necessary we use them the way we do. It makes one wonder in the age of AI and evolving farm practices, can we start finding ways to cultivate already-climate-adapted native bees to do the work? Can we leverage adaptations for specific crops?
I get it that honeybees work great at pollinating monoculture fields, etc., but that does not change the fact we are perpetuating a square peg in round hole problem and pushing it very very far right now, at greater and greater cost, all while climate change is fighting us.
The US was still very much involved in its development and testing, so I think we can still chalk it up as a win for multi-country collaboration, eh :3