Louis Dupont articles - 12 total
How to move beyond Vibe Checking
When developing AI, Vibe Checking is a must. Until a certain point. When you start an AI project,...
Why Most AI Teams Are Stuck 🤔
A few years ago, I worked on a Generative AI project, a customer-facing AI assistant. The company had...
Evaluate your LLM! Ok, but what's next? 🤷♂️
Everyone say you need to Evaluate your LLM. You just did it. Now what? 🤷♂️ You got a score. Great....
DO NOT use these LLM Metrics ⛔ And what to do instead!
In two words: Generalist LLM metrics are more of a danger than an opportunity. NEVER start with...
Error Analysis 🔧 Stop Guessing, Start Fixing AI Models
Error analysis is about digging deep into why something isn’t working - to learn from it. It might...
LLM Evals - The Trap No One’s Telling You 🐔
We hear it more and more: ‘Use LLM Evaluations to guide your AI project.’ And for a good...
📉 Why Improving Your AI Model Is Killing Your Project’s Success
What if improving your AI model is the very thing holding your project back? You’ve spent weeks...
💬 How Intent-Driven Interfaces Will Transform the Way Users Interact with Software
Most software interfaces are frustrating. Users are forced to navigate complex menus, follow rigid...
Turn Your Broken Chatbot 🚧 - Into Your Biggest Asset 📈
You launched your chatbot, and… well, it’s not going as planned. Users are confused, workflows feel...
🤷♂️ ModernBERT Is Here - and It’s Not Just Another LLM Update
BERT is back - and this time, it’s faster, smarter, and built for the tasks that matter. If you’re...
🪤 The Chatbot Trap - Why Your LLM Project Is Stuck After the “Wow Moment"
Your LLM prototype amazed everyone—until it didn’t. Now it’s stuck, and no one’s using it. Here’s...
Why it's time to re-examine the quick vs. clean code debate
The quick code controversy: Why it's time to re-examine the quick vs. clean code debate ...