Christmas CarolPractical AI/ML paper reading — The Platonic Representation HypothesisRead one paper per day to grasp the super basics of a state-of-art AI/ML topic; Minimal Math understanding required, that’s it.4d ago4d ago
Christmas CarolCan a Machine Read Your Mind?Toward Implicit Intent Comprehension in Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs)Jun 11Jun 11
Christmas CarolPractical AI/ML Paper reading: “Lost in the Middle”: How Language Models Use Long ContextsRead one paper per day to grasp the super basics of a state-of-art AI/ML topic; Minimal Math understanding required, that’s it.Apr 30Apr 30
Christmas CarolPractical AI/ML paper reading: “Induction Heads”“Mechanistic interpretability — attempting to reverse engineer the detailed computations performed by the model — offers one possible…Apr 7Apr 7
Christmas CarolPractical AI/ML paper reading: Large Language Models for Data AnnotationRead “useful” ML papers with a PM: Spend two minutes per day to grasp the super basics of a state-of-art AI/ML topic; Minimal Math…Apr 2Apr 2
Christmas CarolPractical AI/ML paper reading: “Mixture of Experts” Explained in 2 minsRead “useful” ML papers with a PM: Spend two minutes per day to grasp the super basics of a state-of-art AI/ML topic; Minimal Math…Mar 31Mar 31
Christmas CarolPractical AI/ML paper reading: How to create a domain specific dataset for LLM…Read “useful” ML papers with a PM: Spend two minutes per day to grasp the super basics of a state-of-art AI/ML topic; Minimal Math…Mar 30Mar 30
Christmas CarolPractical AI/ML Paper Reading — Mamba (State Space Models)Read “useful” ML papers with a PM: Spend two minutes per day to grasp the super basics of a state-of-art AI/ML topic; Minimal Math…Mar 28Mar 28
Christmas CarolPractical AI/ML Paper Reading- PromptBreeder by Google DeepmindRead “useful” ML papers with a PM: Spend two minutes per day to grasp the super basics of a state-of-art AI/ML topic; Minimal Math…Mar 28Mar 28
Christmas CarolAll about LLM EvalsOver the past year, I’ve been engaged in building applications powered by large language models (LLMs), in addition to having extensive…Mar 251Mar 251