I accidentally turned LLM memory into program analysis :: pwning.systems
- Over the past few months I have been playing around quite a bit with LLM agents, particularly for vulnerability research.
- They are becoming surprisingly good at navigating large codebases, explaining unfamiliar subsystems and helping explore potential attack surfaces.
- However, once an investigation starts taking a few hours, I kept running into the same problem: the model would slowly lose track of what we had actually established.
Unverified
- Over the past few months I have been playing around quite a bit with LLM agents, particularly for vulnerability research.
- They are becoming surprisingly good at navigating large codebases, explaining unfamiliar subsystems and helping explore potential attack surfaces.
- However, once an investigation starts taking a few hours, I kept running into the same problem: the model would slowly lose track of what we had actually established.
Sources: Pwning