Where AI Safety Stands

Adrià recently published “Alignment will happen by default; what's next?” on LessWrong, arguing that AI alignment is turning out easier than expected. Simon left a lengthy comment pushing back, and that sparked this spontaneous debate.

Adrià argues that current models like Claude Opus 3 are genuinely good “to their core,” and that an iterative process — where each AI generation helps align the next — could carry us safely to superintelligence. Simon counters that we may only get one shot at alignment, that current methods are too weak to scale. A conversation about where AI safety actually stands.

---

First published:
November 27th, 2025

Source:
https://www.lesswrong.com/posts/zgWhJa9cMCAE9ysoB/will-we-get-alignment-by-default-with-adria-garriga-alonso

Linkpost URL:
https://simonlermen.substack.com/p/will-we-get-alignment-by-default

---

Narrated by TYPE III AUDIO.