diff --git a/README.md b/README.md
index 0dc3549..affee42 100644
--- a/README.md
+++ b/README.md
@@ -16,7 +16,7 @@ By using an LLM as the heart of the translation engine, this system is highly st
 
 According to our evaluations using BLEU score on traditional translation datasets, this workflow is sometimes competitive with, but also sometimes worse, than leading commercial offerings. However, we’ve also occasionally gotten fantastic results (superior to commercial offerings) with this approach. We think this is just a starting point for agentic translations, and that this is a promising direction for MT with significant headroom for further improvement, which is why we’re releasing this demonstration to encourage more discussion, experimentation, research and open-source contributions. 
 
-If agentic translations can generate better results than traditional architectures (such as an end-to-end transformer that inputs a text and directly outputs a translation) -- which are often faster/cheaper to run than our approach here -- this also provides a mechanism to automatically generate training data (parallel text corpora) that can be used to further train and improve traditional algorithms. (See also [this article in The Batch](https://www.deeplearning.ai/the-batch/building-models-that-learn-from-themselves/ on using LLMs to generate training data.) 
+If agentic translations can generate better results than traditional architectures (such as an end-to-end transformer that inputs a text and directly outputs a translation) -- which are often faster/cheaper to run than our approach here -- this also provides a mechanism to automatically generate training data (parallel text corpora) that can be used to further train and improve traditional algorithms. (See also [this article in The Batch](https://www.deeplearning.ai/the-batch/building-models-that-learn-from-themselves/) on using LLMs to generate training data.) 
 
 Comments and suggestions for how to improve this are also very welcome!