Rlhf Websites
ALaRM: Align Language Models via Hierarchical Rewards Modeling
Anonymized project page of ALaRM for review.
Not Applicable
$
8.94
Course Correct Labs — AI Research & Evaluation
Reproducible evaluations for AI behavior: confidence calibration, temporal drift, and delegated introspection. Research-backed tools to keep AI useful, honest, and aligned.
Not Applicable
$
8.94
Nanochat - Full-Stack LLM Training Pipeline | Train LLMs for $100
Open-source LLM training framework by Andrej Karpathy. Minimal, hackable implementation covering tokenizer to SFT. Train a complete LLM in 4 hours for ~$100. Perfect for learning and research.
Not Applicable
$
8.94
