Yeah I agree. I love Rust and Quake is cool, but this is a trivial project for an LLM, and kind of pointless.
It would have been impressive before LLMs, but now? Who cares? Why is this here?
Yeah I agree. I love Rust and Quake is cool, but this is a trivial project for an LLM, and kind of pointless.
It would have been impressive before LLMs, but now? Who cares? Why is this here?
It does have various improvements over the original version. And I don't agree with the notion that "all work that relies on LLMs requires no effort". If this were the case, we would have plenty of complete Rust ports of Quake. It's open-source, allegedly super easy to port. But as far as I know, we did not.
> If this were the case, we would have plenty of complete Rust ports of Quake.
Well no, because there's little point doing it. You want a port of Quake 2 to Rust? Just ask Opus 5.5 to do it. I'm not going to waste the tokens but I guarantee it could do it with no further prompting.
It's literally a best case for AI - it can easily write tests to ensure bit-for-bit identical output and just keep going until it achieves it.
I'm not going to waste the tokens but based on the other stuff I've vibe coded, this was impossible 1 year ago, a difficult challenge 6 months ago, and trivial today.