Key Takeaways from Andrej Karpathy's Deep Dive into LLMs
A summary of the most exciting and surprising aspects of Large Language Models from Andrej Karpathy's 3-hour deep dive video.
I'm a data scientist and strategy consultant with a background in Electronic & Electrical Engineering and Data Science & Machine Learning from UCL. I've worked at Bain & Company's AI Insights & Solutions team, where I sharpened my skills in applied data science and strategic problem-solving. I share my projects, learnings, and writing here - Have a look around!
I write about anything I find interesting to share, but mainly around what I've learnt recently.
Completed the Chartered Financial Analyst Level 1 exam in November 2023, acquiring fundamental knowledge in investment tools, valuing assets, portfolio management, and wealth planning.
Show Credential
Reinforced and advanced my understanding of core ML concepts, including supervised learning, unsupervised learning, reinforcement learning, neural networks, etc.
Show Credential
Developed a strong foundation in deep learning, covering neural network architectures (CNNs, RNNs, LSTMs), backpropagation, optimization, and practical model tuning.
Show Credential