docs: readme update

Author: evilsocket

README.md

@@ -22,7 +22,7 @@
 
 While Nerve was inspired by other projects such as Autogen and Rigging, its main goal and core difference with other tools is to allow the user to instrument smart agents without writing code (unless required for custom functionalities). Another advantage of Nerve is being a single static binary (or docker container) that does not require heavy runtimes (such as Python) while offering maximum efficiency and memory safety.
 
-**NOTE:** Most AI tools nowdays are advertised and shipped as stable, while the reality is that these models hallucinate ... **a lot**. Nerve is an experimental tool. Its API is subject to changes at any time before a stable release is reached. While it is still a valuable learning and experimenting resource, using it in production environments and/or in unsupervised contexts is discouraged. To have an idea of the project readiness, you can `grep -r TODO src` :)
+**NOTE:** The performance of this tool is heavily dependent on the model you use. Bigger models tend to interpret and generate structured data more reliably than smaller ones. If the model you are using generates invalid responses (visible at every step in the statistics), consider using a bigger one of your task.
 
 ## LLM Support