←back to thread

207 points todsacerdoti | 1 comments | | HN request time: 0s | source
Show context
runeks ◴[] No.46005656[source]
I think it would be super interesting to see how the LLM handles extending/modifying the code it has written. Ie. adding/removing features, in order to simulate the life cycle of a normal software project. After all, LLM-produced code would only be of limited use if it’s worse at adding new features than humans are.

As I understand, this would require somehow “saving the state” of the LLM, as it exists after the last prompt — since I don’t think the LLM can arrive at the same state by just being fed the code it has written.

replies(3): >>46005866 #>>46005888 #>>46010197 #
1. rogeliodh ◴[] No.46005888[source]
They are very good at understanding current code and its architecture so no need to save state. In any case, it is good to explicitly ask them to generate proper comments for their architectural decisions and to keep updated AGENT.md file