Update README.md

Thinking about this as a litmus test for agentic codegen capabilities

README.md

@@ -1,4 +1,4 @@
 # chess-codegen
 _Can a codegen agent develop a competitive chess playing program?_
 
-Most people are unable to do it given a few weeks of time. A small number of people can and the resulting programs are small and elegant (e.g. [sunfish](https://github.com/thomasahle/sunfish) is just 131 lines of code). Building this as a test to determine if we are approaching a threshold where agents can engage in non-trivial R&D work and maybe even come up with some fresh ideas via trial and error.
+Most people are unable to do it given a few weeks of time. A small number of people can and the resulting programs are small and elegant (e.g. [sunfish](https://github.com/thomasahle/sunfish) is just 131 lines of code). Building this as my litmus test to determine if we are approaching a threshold where agents can engage in non-trivial R&D work with a high degree of autonomy and maybe even come up with some fresh ideas via trial and error.