GPT — Field Evidence
paperUnverified
GPT · GPT · incident
Field note
Prosody-driven Jailbreaks in Audio LLMs: A Controlled Study and Mechanistic Analysis — Audio-capable foundation models enable end-to-end spoken interaction, but they also introduce safety risks beyond transcript content. It remains unclear how much jailbreak capability can arise
collected 2026-07-30original 2026-07-29
Does this shift the US–China race?
Be the first to call it
Impact on the index
Safety concern · minor
US -15
Directional contribution — before recency decay and per-type diminishing returns. How it works →
Related Front
US vs ChinaLikely
U.S. FrontiervsChina Open-Weight
Likely — capability gap narrowing on common tasks
Letters from the Front
Be the first to file a report.