Update layout/about.md

layout/about.md

@@ -6,6 +6,7 @@
 ## What is this ?
 
 This is a demo meeting Q&A app that retrieves multiple meeting transcripts and answers questions for analysis across meetings.
+
 Context uses retrieval augmented generation (RAG) and the LLM uses the latest [Llama3.1 model](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct). 
 
 
@@ -34,7 +35,8 @@ There are 2 ways to start!
 
 For the purposes of this demo, the pre-stored meetings are a "clean" set of synthetic meetings aimed at inquiring about challenges with meeting effectiveness. I know, how meta. This demo can be taken a step further by using our [fine tuned model](https://huggingface.co/tykiww/llama3-8b-meetingQA) trained both on the alpaca dataset and a *noisy* synthetic dataset of over 3000 product, technical, and academic meetings. Unfortunately, the lack of a persistent GPU on the free Huggingface Zero GPU spaces posed some challenges, so the fancy 3.1 model should do just fine! It's already a massive improvement over the base Llama 3 family of models.
 
-Furthermore, for security purposes, uploaded meetings will only be retained for 1 hour and will automatically be deleted. To query your meetings, please use your specific session key to access the data you uploaded.
+Additionally, in the spirit of a demo, we are trading off accuracy with speed by using a single vector store rather than a carefully crafted node system.
 
+Furthermore, for security purposes, uploaded meetings will only be retained for 1 hour and will automatically be deleted without warning. To query your meetings, please use your specific session key to access the data you uploaded.
 
-This demo is just a peek and is subject to a demand queue. More to come!
+This demo is just a peek. More to come!