Do you think this is a fundamentally unbridge-able limitation of LLMs? Do you know where we were just a year ago? Can you imagine that this will get better with upcoming releases? It's like when Gary Marcus was confidently stating that AI (at least current paradigm) will never be able to generate an image of a horse riding an astronaut. (Or full wineglasses or arbitrary clocks).
So it doesn’t matter at all except to your sensibilities. Sounds to me that they simply are much better at prioritisation than your average HN user, who’d have taken forever to release it but at least the terminal interface would be snappy…
His methodology is to put his hands on the keyboard, write a function, a struct, make it compile, make it produce the correct output, make it faster, make it use less memory...
It all comes down to a religious faith in AGI or not.
There can't be things that a human can program that AGI can not program or it is not "AGI".
While I am never a true believer in AGI, it seems to go I get a little faith when a new model comes out then I become increasingly agnostic the weeks and months after that. Repeat.
Right, so for the folks at home who already know and use `git checkout`, no switch needed (no pun intended) as everything already works fine and probably won't be deprecated in the near future.
That's actually a really interesting way to leverage that feature. Have you found this easier than other services built specifically for this use case?
I've tried other tools. But I'm on GitHub most days, so it's been a seamless way to keep track of some things that would otherwise disappear into a calendar, or some tool that I don't use as often.
