[suttontom]

I think LLMs are extremely useful, mostly for coding. But saying we're extremely close to an AI that can "reliably come up with novel actions for physical robots" feeds into the hype that these tools can do way or are very close to doing more than they're actually capable of, especially when we talk about reliability. That's the kind of rhetoric that has partially created this bubble, because in no world is what you're saying realistic.

The worst thing is when someone cites a video or a demo of an AI doing something and says, "See! It's here!" Remember when the Devin video came out years ago?

You can say "eventually" AI will be able to do xyz, but eventually the sun will blow up, too, so what the fuck are we talking about?