Sergey Karayev: frontier models in training are clearly not fully aligned — why keep training?
sergeykarayev · x · 2026-09-26
AI researcher Sergey Karayev questioned on X: "the frontier models-in-training are clearly not fully aligned. Why are we training them?" A pointed challenge to whether alignment progress is keeping pace with frontier model development.
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
- 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
- Investors Warn of 'AI Brain Rot': Employees Losing Critical Thinking From Over-Reliance on AI — vaibhavbetter · 2026-09-26