Blog

a look inside my head

Literature Review: MAGIC: Near-Optimal Data Attribution for Deep Learning

4 min read · November 22, 2025

2025 · Data Attribution Deep Learning Metalearning AI Interpretability Optimization · research
Literature Review: DAUNCE: Data Attribution through Uncertainty Estimation

4 min read · November 22, 2025

2025 · Interpretability Data Attribution LLM Black-Box AI Uncertainty Estimation · research
Literature Review: Reasoning Models Don't Always Say What They Think

5 min read · November 22, 2025

2025 · Alignment Safety Engineering LLM Chain of Thought Reinforcement Learning Interpretability · research
Literature Review: Anthropic's Project V.E.N.D. 1

3 min read · October 26, 2025

2025 · Agentic AI LLM Human-AI Interaction Simulation · research
Literature Review: In-Context Learning and Induction Heads

3 min read · October 26, 2025

2025 · Mechanistic Interpretability In-Context Learning LLM · research