Sebastian Raschka wraps Reasoning From Scratch series with a deep dive on reasoning-model distillation
rasbt · x · 2026-10-17
Sebastian Raschka released the finale (round 8) of his "Reasoning From Scratch" lecture series on YouTube, covering distillation as an efficient alternative to the reinforcement learning training runs covered earlier.
- Arc: why distill a reasoning model → soft vs. hard distillation → on-policy vs. off-policy distillation → hands-on preparation
- The lecture closes the 8-part series; the author says he'll take a brief break before returning
- Aimed at engineers and researchers wanting a systematic view of reasoning-model training (RL vs. distillation routes)
Related event: Raschka Concludes 'Reasoning From Scratch' Series with Distillation Finale(2 posts)→
More from Research
- Auto-research with Opus 5.5 and GPT6 Astra yields explicit fast matmul schemes on GitHub — IgorCarron · 2026-10-18
- Snorkel AI: 4B model beats 235B on financial analysis for under $500 with RL and verified data — ajratner · 2026-10-18
- tangermeme merges DeepLIFT/SHAP extension bringing attribution to arbitrary models — jmschreiber91 · 2026-10-18
- Tencent's Terminal-RSI lifts terminal agents from 20.7% to 50.6% on Terminal-Bench via recursive self-improvement — omarsar0 · 2026-10-18
- 10 minutes of ultrashort-wave stimulation boosted brain waste clearance in mice — rand_longevity · 2026-10-17
- MIT's IRIS predicts cell fate signals, verified in mouse embryo experiments — alex_verem · 2026-10-17