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)→
More from AGI Musings
- User says ChatGPT outperformed 4 therapists' work of 8 years in one hour — Angaisb_ · 2026-09-26
- Runway CEO: Most breakthroughs are unplanned emergent properties of group collaboration — c_valenzuelab · 2026-09-26
- Sergey Karayev: frontier models in training are clearly not fully aligned — why keep training? — sergeykarayev · 2026-09-26
- Beff Jezos: crypto is the only scalable alignment mechanism for free AIs — beffjezos · 2026-09-26
- Ezra Klein interviews Jensen Huang on AI fears, drawing fire over anti-regulation stance — RobbWiller · 2026-09-26
- WSJ: AI makes entry-level work efficient, but新人 lose the practice that builds skills — mattbeane · 2026-09-26