Featured Posts

• Let's Reproduce GPT-2 by Karpathy - Review

  My notes and takeaways on Andrej Karpathy's GPT-2 reproduction video

  Jan 14, 2025 • 3 min read
  AI Paper

• Transformer Circuits (Anthropic) - Review

  Notes on the mathematical framework behind Transformer models

  Jan 13, 2025 • 6 min read
  AI Paper

• Karpathy's "Let's Build GPT From Scratch" - Review

  My thoughts and notes on Andrej Karpathy's video on building GPT from scratch

  Jan 12, 2025 • 4 min read
  AI Paper Blog

• Curriculum learning for LLMs?

  How can we handle outdated training data in large language models?

  Jan 5, 2025 • 4 min read
  AI Thoughts

• Do LLMs Possess an Internal State of Mind?

  Jan 2, 2025 • 9 min read • Medium
  AI Blog

• Advocating for OpenAI's for-profit model

  An unpopular opinion on OpenAI's transition to a for-profit

  Jan 1, 2025 • 3 min read
  AI Thoughts