flâneur

Daniel Tan on X: "🚨 New paper on alignment midtraining! We stress test alignment midtraining (AMT) at scale. Via systematic ablations, we highlight novel failure modes and identify many critical implementation details required for good performance. We open-source our work. 🧵 👇 https://t.co/6mt4nsCL1A" / X

x.com · saved by 1 readers

🚨 New paper on alignment midtraining! We stress test alignment midtraining (AMT) at scale. Via systematic ablations, we highlight novel failure modes and identify many critical implementation details required for good performance. We open-source our work. 🧵 👇

saved by