TLDR: AI systems are failing in obvious and manageable ways for now. Fixing them will push the failure modes beyond our ability to fix. The AI safety community is also doing a huge economic service to developers. Our belief that our minds can "fix" a super-intelligence - especially bit by bit - needs to be re-thought.

I wanted to write this post forever, but now seems like a good time. The case is simple, I hope it takes you 1min to read.

1. AI safety research is equal to AI capabilities research. We are patching up the most obvious (to us) problems. As time goes we will no longer be able to play this existential risk game of chess with AI systems. I've argued this a lot (preprint; ICML paper accepted, will be out in a few days). Seems others have this thought.
2. Capability development is getting AI [...]

---

First published:

Source:

Narrated by TYPE III AUDIO.