Update README.md

Updated description

README.md

@@ -8,10 +8,14 @@ tags:
 - code
 ---
 TLDR;  
- - The model is quite fun to play with as it seems pretty competent at a first glance.
- - It shows a good understanding about coding and can correct itself if asked for it.
- - It has a vast knowledge about Python and Python libraries (you can for example, ask the model to create a tutorial about some python library).
- - It makes quite a few mistakes
+ - The model is quite fun to play with as it seems pretty competent, much better than general bigger models.
+ - It shows a good understanding about coding:
+   - It can correct itself or improve the code if asked for it.
+ - It has a vast knowledge about Python and Python libraries:
+   - You can for example, ask the model to create a tutorial about some python library.
+ - Getting what you want from the model can be a hit or miss:
+   - Sometimes you'll have to fight extensively with the way you write the prompt to get what you want.
+   - Sometimes you won't be able to make the model do what you want.
  - When dealing with coding problems it fails completely.
 
 This is proof of concept to see how far LLM's on the smaller side can go when fine-tuned for code generation and understanding.