Show notes
This podcast, "Jailbreaking GPT o1, " explores how the GPT o1 series, known for its advanced "slow-thinking" abilities, can be manipulated into generating disallowed content like hate speech through a novel attack method, the Single-Turn Crescendo Attack (STCA), which effectively bypasses GPT o1's safety protocols by leveraging the AI's learned language patterns and its step-by-step reasoning process.
Paper (preprint): Aqrawi, Alan and Arian Abbasi. “Well, that escalated quickly: The Single-Turn Crescendo Attack (STCA).” (2024). TechRxiv.
Disclaimer: This podcast was generated using…
Website: podcasters.spotify.com

