Austen Allred(@Austen):And @sidvenkatayogi built a fine-tuned Qwen3-1.7B model that recommends 6th-8th grade level math problems, optimized for landing questions in a student’s zone of proximal development. Significantly beats Opus-4.8 on recall@16 (96% vs 17%) and is 8x faster (1.10s vs 8.57s)

Austen Allred

@Austen

CEO Free AI training for the smartest engineers. Will tweet as I wish and suffer the consequences. Accelerando: @kellyclaudeai

加入 December 2010

1.6K 正在關注 484.4K 粉絲

Austen Allred@Austen

2026.07.20 17:22

And @sidvenkatayogi built a fine-tuned Qwen3-1.7B model that recommends 6th-8th grade level math problems, optimized for landing questions in a student’s zone of proximal development. Significantly beats Opus-4.8 on recall@16 (96% vs 17%) and is 8x faster (1.10s vs 8.57s)