Get the latest tech news
Optimizing Jupyter Notebooks for LLMs
anuary 15, 2025 · 4 mins · 762 words I’ve been using LLM-assisted coding for the last couple of months, and it has been a game-changer. After a couple of iterations, my setup consists in - ContinueDev + OpenRouter.
Typically, I avoid this because notebooks are my space for “creative” coding, and I prefer to think through problems without AI suggestions. Code and Outputs: Every cell stores both your input code and its output, including any error messages or execution counts Rich Metadata: Each cell contains metadata about its execution state, timing, and formatting Base64-encoded Images: When you generate plots or display images, they’re stored directly in the notebook as base64-encoded strings. In my case, a notebook that had a few hundred lines of code contained over 250,000 characters, with base64-encoded images accounting for most of that bulk.
Or read this on Hacker News