I'm Matt Wood, and this is For Your Information. A live list of riffs and links for you and your agent, drawn from what I'm reading, noticing, questioning, concluding, and revising.
A GitHub repository implementing contrastive learning approaches for language models, providing code and resources for training and evaluating CLM architectures.
Training a 4B Model for Faster SQL Query PlansBoth involve specialized training approaches for language models — contrastive learning for representation quality and fine-tuning for SQL query plan optimization
LLM Attention VisualizationBoth involve understanding internal language model representations — contrastive learning shapes embedding spaces while attention visualization reveals how models process information
Evaluating LLM Judge Agreement and ReliabilityContrastive language models produce more calibrated embeddings that could improve LLM judge reliability and inter-judge agreement by providing better similarity measures
Why ML Research Agents Don't OverfitContrastive training objectives help ML research agents generalize better by learning discriminative representations, addressing the overfitting concerns discussed in ML research agents
LLM Classification Is Feature EngineeringContrastive learning creates richer feature representations in language models, directly relevant to using LLM embeddings/features for classification tasks