I went into rabbit hole of how code auto-complete would work and found out about Fill In the Middle (FIM), documenting my findings. OpenAI's important paper titled "Efficient Training of Language Models to Fill in the Middle" helped
What would human intelligence would have done that AI didn't?
Cloudflare's AutoRAG: A raw, insightful review! Discover its strengths, quirks, and the future of Retrieval-Augmented Generation.
Why did I decide to start with AI? How did it go? What I learnt? And outcomes did I achieve?