Replace PyBot subtitle and introduction with revised copy

site/index.html

@@ -56,17 +56,11 @@
 <body>
 <main>
   <h1>PyBot</h1>
-  <p class="sub">a conversational bot without LLMs</p>
+  <p class="sub">Can Python be a chatbot?</p>
   <div class="text">
-    <p>LLMs drive today's chatbots and agents, but conversational programs are much older than LLMs. Sixty years ago, <a href="https://en.wikipedia.org/wiki/ELIZA" target="_blank" rel="noopener">ELIZA</a> held
-    conversations by matching patterns in what the user typed and answering with predefined templates.</p>
-    <p>We wanted to revisit that idea at a much larger scale, so we gave a swarm of 1k agents the mission of building a chatbot out of
-    plain Python rules (if-else branches, regex patterns and lookup tables). The agents wrote and evaluated over
-    5,000 versions of the bot, and its win rate on <a href="https://huggingface.co/datasets/HuggingFaceSwarms/SmolTalkBench" target="_blank" rel="noopener">SmolTalkBench</a>, where an LLM judge compares each reply with a reference answer,
-    climbed from almost 0% to 26%.</p>
-    <p>The result is PyBot: about 470k lines of Python that answer everyday questions, plus 550k lines of tests the agents wrote to keep
-    it working. On SmolTalkBench it's on par with SmolLM-360M-Instruct (26.0% vs 26.6%), without a single neural network inside. You can
-    try it below, where you can see which of PyBot's modules produced the reply, and you can click any file to read the code behind the answer.</p>
+    <p>LLMs drive today’s chatbots and agents, but chatbots long predate them. Sixty years ago, <a href="https://en.wikipedia.org/wiki/ELIZA" target="_blank" rel="noopener">ELIZA</a> held conversations by matching patterns in what the user typed and answering with predefined templates. It could seem insightful, but its repertoire was narrow, and expanding it meant writing more rules by hand. How far could a rule-based chatbot go if a swarm of agents did that work instead?</p>
+    <p>We challenged a swarm of over 1,000 agents to build a chatbot entirely in Python: no weights, no training, just if-else branches, regex patterns and lookup tables. The agents wrote and evaluated over 5,000 versions, and the chatbot’s win rate on <a href="https://huggingface.co/datasets/HuggingFaceSwarms/SmolTalkBench" target="_blank" rel="noopener">SmolTalkBench</a>, where an LLM judge compares each reply with a reference answer, climbed from 0% to 26%. That puts it on par with SmolLM-360M-Instruct, which just a few years ago was state of the art for models under 1B parameters.</p>
+    <p>The result is PyBot: around 500k lines of code that can answer everyday questions, backed by 550k lines of tests the agents wrote themselves. Try it below: each reply shows which of PyBot’s modules produced it, and you can click any file to read the code behind it.</p>
   </div>
 
   <section class="app" aria-label="Talk to PyBot">