Skip to content

GPT-4V(ision) System Card

Authors: OpenAI (2023)

TLDR (English)

First production-grade multimodal LLM safety/capability disclosure document. Unifies "image + text" into ChatGPT, key step before GPT-4o's end-to-end audio/image/video.

TLDR(中文)

第一份产品级多模态 LLM 的安全/能力披露文档。把"图像 + 文本"统一进 ChatGPT,是 GPT-4o 端到端语音/图像/视频之前的关键一步。