Blog

We checked ChatIBD-2.4's answers to clinician questions, compared it with the same model stripped of its evidence layer, and stress-tested where it still goes wrong. Here is what we found.

GPT-5.6 Luna (Low) matches GPT-5.4-mini, with no material quality difference across models on internal ChatIBD benchmarks

Over 1,000 clinicians have now used ChatIBD. Here's what we learned from six months of real-world use, how we've been testing ourselves, and what's changed in v2.

For as long as I’ve been practising medicine, my goal has been simple: to improve the lives of people with inflammatory bowel disease (IBD). At the Edinburgh IBD Unit, I’ve been involved in everything from introducing...

As a gastroenterologist dedicated to the care of patients with inflammatory bowel disease, I have always believed that access to reliable and well-structured knowledge is one of the greatest tools we can provide in IBD...

Large language models (LLMs) like ChatGPT are impressive generalists, but their breadth is also their limitation. In IBD care, we as clinicians need accurate and reliable information in the flood of guidelines that are published online. We want answers to both simple and complex questions, grounded in trusted guidelines and accurate dosing information...

Hello, and welcome to ChatIBD. Our mission is to create a trusted reference for clinicians navigating the ever-growing number of clinical guidelines in inflammatory bowel disease (IBD)...