It'll do this even in VirtualBox, running about 20x snappier than the native host, which boggles my mind.
It'll do this even in VirtualBox, running about 20x snappier than the native host, which boggles my mind.
At least on most hardware. I have a shitty Dell laptop for work that's basically permanently thermally throttled... :(
This is quite true for LLMs. They can do basic arithmetic, but they can also read problem statements in many diverse mathematical areas and describe what they're about, or make (right or wrong) suggestions on how they can be solved.
Classic AIs suffered the Frame problem, where some common-sense reasoning depended on facts not stated in the system logic.
Now, LLMs have largely solved the Frame problem. It turns out the solution was to compress large swathes of human knowledge in a way that can be accessed fast, so that the relevant parts of all that knowledge are activated when needed. Of course, this approach to flexibility will need lots of resources.
Another point is that you can train a horse, or even eat it if in dire straits. You own that horse. I can't disable things I want to disable, and names, locations, and features change (or are removed) with no notice between minor version updates. I can't tell you the last time I built something for a new Mac, or wanted to.
I don't know MacOS today, and it certainly doesn't make me feel like I own my computer.
I'm less harsh about modern Windows because I view it as amends for Microsoft causing the bot/ransomware crisis of the last 15 years. Still not for me, but at least I neuter it into usefulness.
Maybe I'll spin up an XP VirtualBox off the back of this thread just for old times' sake and see what happens.