David Fischer @davidsebfischer.bsky.social · 26/11/2025We compared kai with one-shot analysis generation by LLMs by scoring the generated Jupyter notebooks based on various criteria. kai consistently outperforms one-shot analysis generation. 110
David Fischer @davidsebfischer.bsky.social · 26/11/2025kai interacts with human scientists through a chat interface in VS Code and directly edits and executes Jupyter notebooks. This design enables kai to autonomously perform analyses while maintaining full accountability. 100
David Fischer @davidsebfischer.bsky.social · 26/11/2025This motivated us to build kai: an agentic AI that uses Jupyter notebooks – the same interface that humans use to collaborate. 100
David Fischer @davidsebfischer.bsky.social · 26/11/2025Agentic AI systems are becoming available for use in science – but can we trust them? 121