Adversarial Code Obfuscation for Defending Against LLM-Based Analysis (arxiv.org) 3 points by dirkc 1mo ago ↗ HN
[–] dirkc 1mo ago ↗ I'm curious about ways to entice agents to perform weird and wacky things when working on a codebase.
1 comment
[ 1.4 ms ] story [ 5.0 ms ] thread