Experimental Features
AI Cockpit Reasoning includes experimental features that are still under development. These features may be unstable, change significantly, or be removed in future versions. Use them with caution and be aware that they may not work as expected.
Warning: Experimental features may have unexpected behavior, including potential data loss or security vulnerabilities. Enable them at your own risk.
Enabling Experimental Features
To enable or disable experimental features:
- Open the AI Cockpit Reasoning settings ( icon in the top right corner).
- Go to the "Advanced Settings" section.
- Find the "Experimental Features" section.
- Check or uncheck the boxes for the features you want to enable or disable.
- Click "Done" to save your changes.
Current Experimental Features
The following experimental features are currently available:
Autocomplete
When enabled, AI Cockpit Reasoning will provide inline code suggestions as you type. Currently this requires the AI Cockpit Reasoning API Provider in order to use it.
Concurrent file edits
When enabled, AI Cockpit Reasoning can edit multiple files in a single request. When disabled, AI Cockpit Reasoning must edit one file at a time. Disabling this can help when working with less capable models or when you want more control over file modifications.
Power Steering
When enabled, AI Cockpit Reasoning will remind the model about the details of its current mode definition more frequently. This will lead to stronger adherence to role definitions and custom instructions, but will use more tokens per message.
Providing Feedback
Join our Discord server where we have channels dedciated to many experimental features. Your feedback is valuable and helps us improve AI Cockpit Reasoning!