RWTHgpt Update Log
In this article you will find an overview of the latest updates of RWTHgpt with the respective changes and new features.
If completely new features are added, a new section will also be created under RWTHgpt features and linked here.
Update from 08.05.2025
Features:
- Share chats: Chats can now be shared with others
Language model (for employees)
- Llama 3
Bugfixes and Improvements:
- When loading branched chats, the last option is now always displayed first
- Used tokens are, if possible, taken directly from the chat responses and no longer calculated separately
- Added info text for slow chat responses
- General design optimizations
- Improved display of formulas
- Improvements in the admin panel:
- API key of access data can no longer be viewed after adding
- Reporting functions have been improved
- Search function: Errors when quickly changing the search word have been fixed
- Reasoning models:
- Title generation now works without errors.
- Code and formulas are displayed correctly in reasoning models
- Images can now be selected correctly when uploading files
- Bugfixes in the admin panel:
- Help page entries are no longer deleted when saving general settings
Update from 20.03.2025
Features:
- Support for models hosted directly by OpenAI
- Multi-client capability
- Added chat search in the sidebar
Language models (new for students):
- OpenAI o1
- OpenAI o3-mini
Bugfixes and Improvements:
- Optimized display of the prompt input field
- Improved display of the editing of prompts
- Preparations for OpenSource models
- User initials now always use the correct font
- An & within generated code is no longer output as &;
Update from 19.12.2024
Bugfixes and Improvements:
- Fixed a bug in the title generation for the chat history for o1 models
Update from 16.12.2024
Bugfixes and Improvements:
- Accessibility improvements
- Page language set correctly
- Integration of semantically labeled headings, attributes and other HTML elements
- Contrast values improved
- Improved use with keyboard
- If errors occur, users are no longer redirected to a separate error page
- Line breaks in prompts are now displayed correctly in the chat history
- Fixed an error when uploading files for o1 models
Update from 11.12.2024
Features:
- Access to RWTHgpt is now also available for all RWTH students. More information can be found in the corresponding blog post.
- Access for students is linked to active status student RWTH status.
Language models (for students):
- GPT-4o
- 6,000 tokens per week
- GPT-4o-mini
- 25,000 tokens per week
Update from 26.11.2024
Features:
- From now on, access to RWTHgpt no longer requires a role in RWTH Identitiy Management.
- Access is now linked to the active status of employee RWTH and FB 10 (in the context of UKA).
Language models:
- GPT-o1-preview is now available
- 25 interactions per hour
- GPT-o1-mini is now available
- 100 interactions per hour with slightly limited functionality
- These models first create a long “chain of thought” internally before responding. The answers are more complex and focused, but the generation can also take longer.
Recommended for use in programming, mathematical or scientific contexts that require complex reasoning.
Bugfixes and Improvements:
- Improved response behavior
- Performance optimization
- Improved readability in the course of accessibility
Update from 26.08.2024
Features:
- Uploaded images can now be actively analyzed by the AI in terms of content
- Prompts issued by RWTHgpt can now be copied directly to the clipboard
- To do this, hold your mouse cursor over a message written by RWTHgpt and select the copy icon at the bottom right of the message
- The message is then copied to your clipboard and can be pasted using the “Right-click” / “Paste” dialog or the “Ctrl” and “V” key combination
- You can now render (mathematical) formulas, for example for the LaTeX software
Language models:
- GPT-4o mini is now available (as default)
- This model allows more interactions (1000 per hour) with slightly limited functionality
- An overview of the existing ChatGPT models, their functions and differences can be found here
Bugfixes and Improvements:
- Deleted chats no longer remain visible in the navigation bar
- The reply text generation of RWTHgpt for longer replies can now be interrupted without issues
- The design has been harmonized and improved across the board
- Error messages have been adjusted and should now better summarize why an error has occurred
- RWTHgpt can now handle pasted code better and perform more tasks with it
- Code pasted into prompts or output by RWTHgpt now has better syntax highlighting
- Database query performance has been improved
Introduction on 17.07.2024
Features:
- All functions that are available at the start of the RWTHgpt service can be viewed under RWTHgpt features.
Language models:
- ChatGPT-3.5 and ChatGPT-4o are available at the start of the service
- Depending on the selected language model or AI tool, there are different interaction limits