Almanac
model

GPT-4V

modelactivegpt-4v-46b8be99·2 events·first seen 28d ago

Aliases: GPT-4V

Co-occurring entities

More like this (12)

Recent events (2)

7Openai Blog·28d ago·source ↗

GPT-4V(ision) System Card

OpenAI published the system card for GPT-4V(ision), the multimodal extension of GPT-4 that accepts image inputs alongside text. The document covers capability evaluations, safety assessments, and known limitations of the vision-enabled model. It represents OpenAI's formal safety and transparency disclosure accompanying the GPT-4V release.

8Openai Blog·28d ago·source ↗

ChatGPT can now see, hear, and speak

OpenAI announced multimodal capabilities for ChatGPT, enabling the model to process images (vision), listen to voice input, and respond with synthesized speech. These features expand ChatGPT beyond text-only interaction into a multimodal assistant experience. The rollout was announced for Plus and Enterprise users first, with broader availability to follow.