michaelmior

FWIW, almost this exact syntax for imports (without the `npm:` prefix) is supported for standalone scripts with Bun.

I recently discovered Charles Soule who started in comic books and ventured into novels. I read The Oracle Year recently and now I'm reading The Endless Vessel.

I remember using a Maemo device circa 2009. I recall overall really liking the OS.

I personally really enjoyed Watch Dogs: Legion. It wasn't so much that each individual was very unique. Moreso the concept of being able to become anyone.

> you lose all the users who don't want to leave the walled garden, even though they can.

I think it's moreso you lose all the users who don't realize anything outside the walled garden even exists.

> an advantage of agents in huge codebases is that they can find where to make the change and draft it, which wouldn't work with this system.

I think you could go meta here and ask the agent in English to modify your pseudocode for larger changes.

While excessive screen time can certainly be a problem and the specific content matters there is nothing inherently wrong with a small amount of age-appropriate YouTube content consumption.

The announcement didn't read as AI-generated to me at all. Of course this is far from foolproof, but ZeroGPT says 0% AI.

I'm curious what you think makes this better than the dozens of sites out there that have the same goal?

Some changes certainly can be. If the model produces the exact same output for a fixed seed across a variety of inputs after a code change, I think it's reasonable to expect that the change is correct. There are also mathematical transformations that can be applied in some cases that are provably correct. (Not suggesting there's necessarily anything of this nature that will lead to 1,000x improvement though.)

This depends on what your workflow is. There are use cases for tokenization that don't always involve immediately feeding the text into a model.