FrontierThe story, in brief

Thinking with images

OpenAI o3 and o4-mini now reason WITH images, not just about them. Chain-of-thought visual perception is a new capability tier.

Illustration of a transparent lens revealing connected networks across layers of paper.
Exploring the next frontier of AI research.AI illustration by KeyNews
The KeyNews take

Why it matters

OpenAI's o3 and o4-mini models introduce visual reasoning directly into chain-of-thought processing, expanding multimodal capabilities beyond image recognition to true visual reasoning. This represents a material shift in how vision-language models process and understand images.

The key facts

4 to know
  1. OpenAI releases o3 and o4-mini with visual reasoning in chain of thought

  2. Models can now reason WITH images as part of their reasoning process

  3. Represents breakthrough in multimodal perception capabilities

  4. Capability: visual perception through reasoning chains

Go to the source

OpenAI Blogopenai.com

Publisher excerpt: OpenAI o3 and o4-mini represent a significant breakthrough in visual perception by reasoning with images in their chain of thought.
Read original report
Back to today's editionMore frontier news

The wider picture

View all
Illustration of a transparent lens revealing connected networks across layers of paper.
AI illustration by KeyNews
Frontier01

Alibaba's open-weight Qwen-Image-2.1 claims to beat closed models in image generation with just 7 billion parameters

A capable open-weight image model at 7B parameters challenges the closed-model dominance in generation and editing, expanding practitioner options for on-device and cost-efficient image workflows.

The Decoder
Illustration of a transparent lens revealing connected networks across layers of paper.
AI illustration by KeyNews
Frontier02

Tencent's Gander aims to keep talking while it works in the background

A novel architecture for multimodal agents that separates conversational continuity from task execution. Demonstrates a real capability tradeoff: smoother UX vs. task reliability. Relevant to how frontier labs are rethinking agent design.

The Decoder
Illustration of a transparent lens revealing connected networks across layers of paper.
AI illustration by KeyNews
Frontier03

Simulated students that make realistic mistakes help AI tutors learn faster

A novel approach to AI training using realistic synthetic feedback loops is accelerating tutor model development and reducing the cost of evaluation data. This represents a meaningful shift in how frontier labs can iterate on capability without massive labeled datasets.

The Decoder