Machine Learning Advanced
TRACE: Train Agents on Their Own Failures With GRPO
Diagnose an agent's missing skills, then train targeted, routed LoRA adapters with GRPO.
10 min read·Kodetra Technologies
21d agoGuides
AI Guides for Builders
How-to content for builders, indie hackers, and AI engineers. Less theory, more shipped code.
Machine Learning 
Machine Learning Intermediate
GRPO Fine-Tuning: Train Reasoning Into Small LLMs
Use GRPO to teach a 0.5B model multi-step math reasoning end to end.
9 min read·Kodetra Technologies
Apr 30