You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Looking at the screenshot, I can see the bug:
The AI is not properly implementing the styling changes. Instead, it's just acknowledging them with messages like:
"I see the app is now rendering but there's a small styling issue..."
"Improve styling to make it more modern and polished..."
"You did not make any changes"
The issue is that even though we're in iterative mode and taking screenshots, the prompt we're sending with the screenshots isn't effectively triggering the AI to take action. It's just making the AI describe what it sees rather than implementing the changes.
The AI should be:
Seeing the styling issues in the screenshot
Creating/updating the necessary CSS files
Implementing the styling changes directly
Instead, it's just creating a chain of observations without taking any action. We need to modify the prompt to be more action-oriented and explicitly tell the AI to implement the changes it sees are needed.
Link to the Bolt URL that caused the error
na
Steps to reproduce
Well i just created from a todo app in Tailwind and then sent a screenshot where my preview was blank and this contineud to happen. It just shows generic title of the change that need to be made then doesnt actually do it
Expected behavior
It should say "Created xxx file. Updated xxx file" as it normally does
Screen Recording / Screenshot
Platform
OS: [e.g. macOS, Windows, Linux]
Browser: [e.g. Chrome, Safari, Firefox]
Version: [e.g. 91.1]
Provider Used
No response
Model Used
No response
Additional context
No response
The text was updated successfully, but these errors were encountered:
Describe the bug
Looking at the screenshot, I can see the bug:
The AI is not properly implementing the styling changes. Instead, it's just acknowledging them with messages like:
"I see the app is now rendering but there's a small styling issue..."
"Improve styling to make it more modern and polished..."
"You did not make any changes"
The issue is that even though we're in iterative mode and taking screenshots, the prompt we're sending with the screenshots isn't effectively triggering the AI to take action. It's just making the AI describe what it sees rather than implementing the changes.
The AI should be:
Seeing the styling issues in the screenshot
Creating/updating the necessary CSS files
Implementing the styling changes directly
Instead, it's just creating a chain of observations without taking any action. We need to modify the prompt to be more action-oriented and explicitly tell the AI to implement the changes it sees are needed.
Link to the Bolt URL that caused the error
na
Steps to reproduce
Well i just created from a todo app in Tailwind and then sent a screenshot where my preview was blank and this contineud to happen. It just shows generic title of the change that need to be made then doesnt actually do it
Expected behavior
It should say "Created xxx file. Updated xxx file" as it normally does
Screen Recording / Screenshot
Platform
Provider Used
No response
Model Used
No response
Additional context
No response
The text was updated successfully, but these errors were encountered: