Sergey Karayev asks: if frontier models in training aren't aligned, why train them?

sergeykarayev · x · 2026-09-26

Sergey Karayev sparked discussion by asking a pointed question: frontier models currently in training are clearly not fully aligned, so why keep training them? He asked for a plain-language explanation of the industry's reasoning, touching on the core tension between AI safety concerns and the competitive race to scale.

Related event: Researcher Questions Training Frontier Models Despite Misalignment(2 posts)→

Original post →

More from AGI Musings

AGI Musings channel →