EPISODE · Apr 18, 2026 · 7 MIN
The Architecture of AI Assistants: A Guide to LLM Post-Training
from Steven AI Talk · host Steven
Post-training is the critical bridge between a raw base model and a helpful AI assistant. This guide breaks down the essential phases of supervised fine-tuning (SFT) and preference alignment that define modern LLM development.Technical highlights:Transitioning from next-token prediction to instruction following.The "accuracy-diversity-complexity" triad of high-quality data.Why DPO is replacing PPO in the preference alignment stack.Model merging: Combining specialized architectures without retraining costs.Evaluating with LLM-as-a-judge to handle open-ended complexity.The next frontier? Test-time compute scaling to solve the most difficult reasoning challenges.All my links: https://linktr.ee/learnbydoingwithsteven #learnbydoingwithsteven #LLM #PostTraining #AI #MachineLearning #DPO #ModelMerging #DataScience #AIEngineering #MIT
What this episode covers
Post-training is the critical bridge between a raw base model and a helpful AI assistant. This guide breaks down the essential phases of supervised fine-tuning (SFT) and preference alignment that define modern LLM development.Technical highlights:Transitioning from next-token prediction to instruction following.The "accuracy-diversity-complexity" triad of high-quality data.Why DPO is replacing PPO in the preference alignment stack.Model merging: Combining specialized architectures without retraining costs.Evaluating with LLM-as-a-judge to handle open-ended complexity.The next frontier? Test-time compute scaling to solve the most difficult reasoning challenges.All my links: https://linktr.ee/learnbydoingwithsteven #learnbydoingwithsteven #LLM #PostTraining #AI #MachineLearning #DPO #ModelMerging #DataScience #AIEngineering #MIT
NOW PLAYING
The Architecture of AI Assistants: A Guide to LLM Post-Training
No transcript for this episode yet
Similar Episodes
No similar episodes found.
Similar Podcasts
No similar podcasts found.