improve

Author: dphuang2

blog/2024-11-18-llm-pmf/llm-pmf.mdx

@@ -81,17 +81,16 @@ extraction and search problem** that's perfect for automation.
 
 ## Conclusion
 
-When building an LLM startup, focus on problems with these key characteristics:
+When building an LLM startup, focus on problems with two key characteristics:
+
+ - Low Entropy - solutions follow common patterns, as seen in coding
+ - High margin of error - tasks like copywriting where art trumps science
+
+Or can be solved in a simlar way to common well-suited problem types such as:
 
- - Low Entropy
- - High margin of error
  - Search
  - Document extraction
 
-Problems requiring high precision or having high entropy may not be suitable for
-LLMs. However, LLMs can still excel at predictable tasks, as seen in copywriting
-and coding assistance.
-
 Beyond traditional business evaluation, ask yourself: "Are LLMs particularly
 well-suited to solve this problem?" If not, reconsider unless you have unique
 insights into making it work.