# OpenAI — CLIP: Connecting text and images

- Company: OpenAI (openai.com)
- Announced: 2021-01-05T08:00:00+00:00
- Category: new-model
- Coverage: not counted
- Announcement: yes
- Group: models
- Source: https://openai.com/index/clip
- Record: https://forck.live/items/939-clip-connecting-text-and-images
- Subject: GPT / ChatGPT / API
- Models affected: CLIP

OpenAI introduces CLIP, a neural network that learns visual concepts from natural language supervision and can be applied to visual classification benchmarks in a zero-shot manner.

## Evidence

Verbatim from https://openai.com/index/clip:

> We’re introducing a neural network called CLIP which efficiently learns visual concepts from natural language supervision.

---

Record: https://forck.live/items/939-clip-connecting-text-and-images
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md