Codex Now Allows Running Agents on Selected Models
Codex Now Allows Running Agents on Selected Models
Codex now enables users to run agents on chosen models, opening up new possibilities for customization.
Codex Now Allows Running Agents on Selected Models
Codex now allows users to run an agent on a specific model of their choice. This feature provides users with greater flexibility in customizing their projects and experimenting with different models.
In the demo, you can observe how Codex runs all possible combinations of models and levels of thinking effort to build the same website in MagicPath. This showcases the power and adaptability of Codex when working with various AI models.
Why it matters
AnalysisThis new feature empowers Codex users to leverage AI more effectively for project creation, potentially enhancing productivity and creativity in development.
Discuss in community
Share your questions and insights with developers
Related in Ecosystem
Practical guides, core terminology, and agent skills
Codex: Basic Onboarding, Setup, and First Tasks
There are three ways to work with AI when writing code - and Codex covers the most ambitious of them.
ChatGPT Updates: Plugin Development and Codex Workflows
Comprehensive engineering guide to creating, packaging, testing, and submitting plugins for ChatGPT and Codex: manifest specification, MCP servers, lifecycle hooks, custom marketplaces, and OpenAI review.
Short-Term and Long-Term Memory of Agents
The architecture of multi-tier memory for autonomous agents. It distinguishes between Short-Term Memory (active context window of the current session) and Long-Term Memory (vector databases, user profile files, and episodic diaries).
MIT researchers show GPT-6 Astra can improve other AI models by editing their weights
In an experiment, Astra raised Qwen3.5-0.8B's accuracy on MATH-500 from 7.9% to 48.1% by changing only 0.016% of the model's weights.