The GPT-4V(ision) system card <link below> was published on September 25, 2023, by OpenAI. It introduces GPT-4’s capability to analyze image inputs, marking a significant advancement in multimodal large language models (LLMs).

GPT-4V, as game-changing as code interpreter, allows users to instruct GPT-4 to analyze image inputs. This is seen as a major step in AI research, expanding the impact of language-only systems by adding novel interfaces and capabilities.

Some of its features:

  • Versatile in analyzing both complex and everyday images.
  • Transforms educational settings with in-depth image interpretation.
  • Capable of understanding deeper meanings, like group dynamics.
  • Revolutionary but still evolving, with occasional errors.

Examples (! see also Twitter/X links below the demo video):

  • Image to code:
  • Object recognition:
  • Financial analysis:

GPT-4V is rolling out as of September 24th and will be available in both the OpenAI ChatGPT iOS app and the web interface. You must have a GPT-4 subscription to use the tool.

An impressive demo below:

The GPT-4(ision) system card:

GPT-4V(ision) system card
GPT-4 with vision (GPT-4V) enables users to instruct GPT-4 to analyze image inputs provided by the user, and is the latest capability we are making broadly available. Incorporating additional modalities (such as image inputs) into large language models (LLMs) is viewed by some as a key frontier in a…