3 points | by damienmeur 5 hours ago ago
2 comments
Pure statistics and AST history over throwing another LLM at the problem is such a refreshing approach. Super clever project, congrats!
Thank you very much ! :) The idea was indeed to not rely on LLM to watch LLMs, also making it pure stats allow ultra fast feedback loop. I tried a lots of different techniques, but well refined stats outperforms all neural network techniques
Pure statistics and AST history over throwing another LLM at the problem is such a refreshing approach. Super clever project, congrats!
Thank you very much ! :) The idea was indeed to not rely on LLM to watch LLMs, also making it pure stats allow ultra fast feedback loop. I tried a lots of different techniques, but well refined stats outperforms all neural network techniques