supervised-fine-tuning

# curriculum-learning → post-training → reinforcement-learning → supervised-fine-tuning

1 link tagged with all of: curriculum-learning + post-training + reinforcement-learning + supervised-fine-tuning

Click any tag below to further narrow down your results

Links

The State of AI Post-Training Agents

This article updates FrogsGame results using Claude Fable 5, Opus 4.8, and GPT-5.5 to see how AI agents have improved at post-training a base model. Fable 5 solved the key failure of low-quality SFT traces by programmatically generating correct reasoning with a backtracking algorithm, then fine-tuning and RL within the time budget, boosting pass@4 and calibration. It also improved time use, data diversity, curriculum strategies, and error recovery.

Last saved Jun 24, 2026 · 6 min read

+ frogs-game post-training supervised-fine-tuning reinforcement-learning curriculum-learning