How to Measure the Quality of Generative AI—Without the Guesswork
As we’ve been building AI agents recently, we’ve spent considerable time reflecting on how to effectively measure the output quality from these large language models (LLMs). Let’s break down three key observations we’ve made: 1. Measuring AI in Real-World Contexts Standard benchmarks provided by LLMs, such as MMLU, offer generalized evaluation techniques that help […]
Beyond the Hype: Practical Tips for Selecting AI Tools
Best Practices for AI Tool Selection A lot of people have been asking us which AI tools we use and how we keep up with all the options out there. But I think there’s a more critical question we should be asking. What do you aim to achieve with AI tools, and how can […]
Mastering the Balance: Creating with GenAI
In the digital age, there’s a prevailing misconception that everything should be either painstakingly manual or instantaneously automated. But, as I recently discovered while creating my first newsletter with GenAI, the most effective approach usually lies somewhere in the middle. Utilizing GenAI purely for speed, without adding personal insights, is akin to cutting corners—it’s […]
