Hamel & Shreya's LLM Evals Course: Lesson 1
Notes from the first lesson of Parlance Lab's Maven course on evaluating LLM applications - covering the Three Gulfs model and why eval is where most people get stuck.
Artificial intelligence
Synthesising a new framework for AI Transformation
I like bits of Brunig's and Mollick's AI frameworks, but neither quite works for me.
Error Analysis for Improving LLM Applications
A systematic approach to analysing and improving large language model applications through error analysis.
Why we need Experiment-based Roadmaps in the AI Product Era
Why evaluation-driven experimentation creates better roadmaps in AI products.
The challenges of mastering LLMs, and their role as cyborg enhancement
Simon Willison was a guest on Logan Kilpatrick's Google podcast. Topics covered: AI as a 'cyborg enhancement', the non-intuitive challenges of mastering LLM use, and the legitimate need for uncensored language models in fields like journalism.
How AI is making its way into Government
Exploring AI's role in government: from sanctioned projects to unapproved staff use, and its creeping integration into everyday tools.