| ▲ | Adversarial Code Obfuscation for Defending Against LLM-Based Analysis(arxiv.org) | |
| 3 points by dirkc 17 hours ago | 1 comments | ||
| ▲ | dirkc 17 hours ago | parent [-] | |
I'm curious about ways to entice agents to perform weird and wacky things when working on a codebase. | ||