Researcher Questions Training Frontier Models Despite Misalignment

AI researcher Sergey Karayev sparked debate by asking why frontier models continue to be trained despite being visibly misaligned. The discussion touches on the tension between AI safety and the pace of AI development.

2026-09-26 ~ 2026-09-26 · 2 related posts

• Sergey Karayev: frontier models in training are clearly not fully aligned — why keep training? — sergeykarayev · 2026-09-26

1 near-duplicate retellings: sergeykarayev