Updated details

app.py

@@ -153,7 +153,9 @@ with block:
                 <p>Powered by <a href='https://openai.com/'>OpenAI</a>, <a href='https://arxiv.org/'>arXiv</a> and <a href='https://github.com/hwchase17/langchain'>LangChain 🦜️🔗</a></p>
                 <p>ArxivGPT is a chatbot that answers questions about research papers. It uses a pretrained GPT-3.5 model to generate answers.</p>
                 <p>Currently, it can answer questions about the paper you just linked.</p>
-                <p>It's still in development, so please report any bugs you find. It can take up to a minute to start a conversation for every new paper as there is a parsing delay.</p>
+                <p>It's still in development, so please report any bugs you find. </p>
+                <p>It can take up to a minute to start a conversation for every new paper as this is just a demo hosted on a lightweight service.</p>
+                <p>For best results, host it on better GPUs. Took 20 seconds to start on M1 Chip</p>
                 <p>The answers can be quite limited as there is a 4096 token limit for GPT-3.5, hence wait for GPT-4 access for better quality.</p>
                 <p>If you don't get a response for GPT-4, it is likely that you don't have API access, try 3.5</p>
                 <p>Possible upgrades coming up: faster parsing, status messages, other research paper hubs.</p>