Questions in README are answered

README.md

@@ -168,6 +168,11 @@ Simply put, this downloads the file as a temp file, we load it in with `TextFile
 
 Why do we want to support streaming? What about streaming is important, or useful?
 
+- Enhanced responsiveness: streaming allows applications to display output progressively reducing perceived latency
+- Reduced wait times: LLMs can take several seconds to generate full responses; streaming enables users to see partial results as they are produced
+- Real-time interactions: streaming allows for real-time interactions efficiently while providing a smoother and more engaging user experience.
+
+
 ### On Chat Start:
 
 The next scope is where "the magic happens". On Chat Start is when a user begins a chat session. This will happen whenever a user opens a new chat window, or refreshes an existing chat window.
@@ -210,6 +215,11 @@ Now, we'll save that into our user session!
 
 Why are we using User Session here? What about Python makes us need to use this? Why not just store everything in a global variable?
 
+- User Session: 
+    - Allows for stateful applications: User sessions enable applications to maintain state between requests, which is crucial for chat applications where context is important.
+    - Supports concurrent users: User sessions allow multiple users to interact with the application concurrently, which is essential for chat applications.
+    - Provides a clean interface: User sessions provide a clean interface for managing application state, making it easier to develop and maintain applications.
+
 ### On Message
 
 First, we load our chain from the user session:
@@ -330,8 +340,16 @@ Try uploading a text file and asking some questions!
 Upload a PDF file of the recent DeepSeek-R1 paper and ask the following questions:
 
 1. What is RL and how does it help reasoning?
-2. What is the difference between DeepSeek-R1 and DeepSeek-R1-Zero?
+
+    - Reinforcement Learning (RL) is a type of machine learning that involves an agent learning to make decisions by interacting with an environment and receiving rewards or punishments for its actions. RL helps reasoning by allowing an agent to learn from its experiences and improve its decision-making over time.
+
+2. What is the difference between DeepSeek-R1 and DeepSeek-R1-Zero? TLDR: the training process is different.
+    DeepSeek-R1-Zero has powerful and intriguing reasoning behaviors. However, it encounters challenges such as poor readability, and language mixing. To address these issues and further enhance reasoning performance, DeepSeek-R1 was introduced, which incorporates multi-stage training and cold-start data before RL. 
+    
+    DeepSeek-R1 achieves performance comparable to OpenAI-o1-1217 on reasoning tasks.
+
 3. What is this paper about?
+    - This paper is about the DeepSeek-R1 model, a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary step. 
 
 Does this application pass your vibe check? Are there any immediate pitfalls you're noticing?