Update index.html

index.html

@@ -109,16 +109,16 @@
             core. Everyone who took "Machine Learning 101" knows that the <i>k</i>-nearest
             neighbor classifier is among the simplest yet most robust ML classifiers out
             there, perhaps only beaten by the Naive Bayes classifier. So what happens if
-            you train a <i>k</i>-NN classifier to predict words? ...
+            you train a <i>k</i>-NN classifier to predict words?
           </p>
           <p>
-            A memory-based language model, in this case running on the 
+            WOPR's engine is the 
             <a href="https://github.com/LanguageMachines/timbl">TiMBL</a> classifier,
-            is in the most basic sense a <i>k</i>-nearest neighbor classifier. However, on
-            tasks like next-word prediction, <i>k</i>-NN becomes inhibitively slow. Fortunately,
+            which implements a number of fast approximations of <i>k</i>-NN classification, 
+            all partly based on decision-tree classification. On
+            tasks like next-word prediction, <i>k</i>-NN is inhibitively slow, but the
             <a href="https://github.com/LanguageMachines/timbl">TiMBL</a> 
-            offers a number of fast approximations of <i>k</i>-NN classification, all
-            partly based on decision-tree classification and many orders of magnitude faster.
+            approximations can classify faster at many orders of magnitude.
           </p>
           <p>
             Compared to Transformer-based LLMs, on the plus side memory-based LLMs are
@@ -138,6 +138,8 @@
               but we have not trained
               beyond data set sizes with orders of magnitudes above 100 million words.
               Watch this space!</li>
+            <li>They <b>do not have a delicate attention mechanism</b>b>, arguably the killer feature
+              of Transformer-based decoders;</li>
             <li>Memory requirements during training are <b>heavy with large datasets</b> 
               (more than 32 GB RAM with more than 100 million words);</li>
             <li>Memory-based LLMs are not efficient at generation time when running relatively