1. Funktionen
  2. Pricing
  3. Forum
    1. Articles
  4. App starten
AI News
  • Everywhere
  • AI News
  • Articles
  • Pages
  • Forum
  • Products
  • More Options
  • Login
  • Register
  • Search
  1. Aivor
  2. Articles
  3. AI News

ChatGPT expands its features: try-ons, PDF scanning and Codex Cloud

  • Daniel Böhmel
  • October 2, 2026 at 8:31 AM
  • 75 Views
  • 0 Comments
  • by Daniel Böhmel
OpenAI is turning ChatGPT into a versatile toolbox: users can virtually try on clothes, scan multiple document pages into a PDF and continue coding tasks in isolated cloud environments.
Contents [hideshow]
  1. ChatGPT scans multiple pages into a PDF
  2. Codex Cloud keeps tasks running
    1. Sources

ChatGPT is becoming a shopping platform, document scanner and development environment. The new features that OpenAI announced or made available at the end of September and on October 1, 2026, are pushing the service further beyond the traditional chat window. Anyone who previously only asked questions now gets tools for clothing, paperwork and code.

For clothing and accessory listings, a “Try on” button may appear in ChatGPT. Users can take a selfie or upload an existing photo for this purpose. The reference photo can be changed or deleted in the settings under “Personalization → Reference photos.” It is certainly practical, because when shopping online, the question of fit otherwise tends to get stuck somewhere between the product image and the return package.

Found products can also be saved as favorites. They can likewise be stored in folders in the ChatGPT library. This turns individual finds into a sortable collection instead of letting them disappear in the chat history.

ChatGPT scans multiple pages into a PDF

Also on October 1, 2026, OpenAI announced an iOS rollout for scanning notes and documents. Multiple pages can be captured one after another with the ChatGPT camera and then automatically combined into a PDF file. This PDF can subsequently be uploaded to a chat.

According to the release notes, users start via the camera, the three-dot menu and the “Scan” option. That may sound unremarkable, but it is exactly the kind of feature that eliminates a small everyday detour: capture pages one after another, combine them and then use them in the chat. The scanner is therefore no longer a separate device sitting somewhere next to the printer, but part of the described iOS feature.

Codex Cloud keeps tasks running

“Codex Cloud” has been available since September 29, 2026. Coding tasks can be started and continued across desktop, web or mobile devices. Reusable environments can contain repositories, tools and dependencies. Each task gets an isolated workspace and can continue running when the computer is inactive.

For ChatGPT Enterprise, OpenAI also mentions shareable cloud environments for eligible members. This is clearly aimed at workflows where not everyone should have to start from scratch. The computer can be turned off in the meantime. Apparently, the code does not wait reproachfully on the screen.

On the same day, OpenAI introduced “GPT-6.1 Sol” for Codex and ChatGPT Work. The rollout began for Pro users and is scheduled to expand to Plus, Business, Enterprise and Edu. According to OpenAI, the model was improved for agentic coding, computer use and professional work.

Enterprise and Edu administrators can enable model access in the workspace settings. This means availability in these areas depends not solely on a user’s personal preference, but also on the decision made within the respective workspace. So ChatGPT is gaining more use cases and more switches at the same time.

The common thread among these innovations is not merely another chat mode. ChatGPT is intended to categorize products using a reference photo, bundle paper pages into a PDF and continue coding tasks in isolated environments. This is less the digital version of a friendly conversation and more a toolbox that keeps expanding beyond the chat.

Sources

  1. ChatGPT — Release Notes | OpenAI Help Center
  2. Release Notes | OpenAI | OpenAI

See more of us in Google search results: add us as a preferred source.

Add as preferred source on Google

Written by

Daniel Böhmel
Software Developer

Daniel Böhmel has been developing software for over 20 years and has been self-employed since 2007. He started out with interactive web design back in the Flash era; later, he built his own online projects, such as a fitness forum and a supplement store, including the editorial content. Today, his…

View the profile of Daniel Böhmel
  • chatgpt
  • Codex Cloud
  • Document scanning

Previous Article AI opponents have already lost - they just don't know it yet

Next Article Gemini 4 Argon, Skills, and Guided Vision: Google's Overhaul

Participate now!

Don’t have an account yet? Register yourself now and be a part of our community!

Register Yourself Login

Categories

  1. AI Agents 11
  2. AI News 23
  3. Creating AI Content 28
  4. AI Community 11
  5. Prompt Engineering 15
  6. Ticket System 8
  7. AI Technology 14
  8. Chatbots 12
  9. Reset Filter

Most popular articles

  • Stable Diffusion Face Swap with ReActor: Guide for ComfyUI, Forge and img2img

    11,112 Views
  • Cross-Disciplinary Collaboration in the AI Community: Case Studies and Success Stories

    7,310 Views
  • The 5 best AI robots for the home: a comprehensive overview

    6,592 Views
  • Learn everything about our AI forum

    6,271 Views
  • The ultimate guide: How to write perfect AI prompts for ChatGPT & Co.

    4,192 Views

Artificial intelligence articles

Discover our collection of articles on artificial intelligence. Learn all about the latest developments and applications of AI technology. Our articles cover a variety of topics, from Machine Learning and Deep Learning to Robotics and Autonomous Systems. Read our articles to get a comprehensive overview of AI technology and stay up to date with the latest developments in this exciting field.


Show all AI articles

  1. Usage policy
  2. Terms and conditions
  3. Editorial
  4. Privacy Policy
  5. Contact
  6. Legal Notice