Hinted scaling laws allow you to make better benchmark accuracy forecasts!
Stanford AI Lab(@StanfordAILab) · 人工智能
Hinted scaling laws allow you to make better benchmark accuracy forecasts! Suze van Adrichem @suze_va Can we forecast benchmark accuracy from models that score zero? We (co-leads @LukeBailey181 @rckpudi ) turn a benchmark into a series of easier hinted versions. Jointly modeling scale C and hint level H enables forecasting GSM8K acc (H=0) within 3 pts from 5600x less compute 🧵 🔗 View Quoted Tweet 💬 1 🔄 1 ❤️ 5 👀 1456 📊 2 ⚡ Powered by xgo.ing