GPT-Live system card: some safety metrics regress after evaluation configuration correction
Original title:GPT-Live System Card
AI summary
OpenAI released the system cards for GPT-Live-1 and GPT-Live-1 mini and reran voice-native prohibited content evaluations after discovering a mismatch in evaluation configurations.
Quick Facts
- Published
- Updated
- Source
- OpenAI:部署安全与系统卡(网页)
- Category
- Model Releases
- AI score
- 60
OpenAI 公开更正后的语音安全评测数据,附带修正前后对照,读者可看到误配置如何影响安全评估结论。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: GPT-Live system card: some safety metrics regress after evaluation configuration correction. July 8, 2026. https://new.nat6.net/en/news/ilmtw6i4nlldfqw9e7huv99aa/