#ai #langchain #python #reading-list
When Jack and I set out to help people safely use their data with Generative AI, we thought we understood the problem space. We'd worked with governments and pharma companies on getting "classical" AI to be useful on extremely sensitive data. But that experience only partly applied: the basic lessons (like the importance of good data prep) were still relevant for LLMs, but we had to learn many new tactics in how to apply these lessons.
Since then we've been extremely lucky to work with some amazing Enterprises, with thousands of employees and tons of complex, real-world data and usecases for Generative AI. Thanks to their early trust, we've seen many subtleties about what's needed to make systems work. We thought it would be helpful for developers who are starting out on their journey building AI applications for us to transparently share some of these learnings, so that they don't need to repeat the same mistakes we made!
⚠️ This post links to an external website. ⚠️
If this post was enjoyable or useful for you, please share it! If you have comments, questions, or feedback, you can email my personal email. To get new posts, subscribe use the RSS feed.