AI Regulation, Safety & Geopolitics ・ 🚨 Incidents and misuse

LLM Jailbreaks Explained: Prompt-Layer Attacks, Not Bugs

OrcaRouter · 10/21 11:13 UTC

A jailbreak edits the prompt, not the weights. The article covers what measured success rates show, why there is no per-model answer, and which controls change the rate.

Read the original (OrcaRouter)

See it in the digest → ・ See this issue →