Conversation
There was a problem hiding this comment.
Pull Request Overview
This PR updates the messaging in the ProcessingHelper to reflect that three solution approaches—including a brute-force better approach and an optimal solution—are now being generated.
- Updated progress status messaging to include "brute-force better-approach".
- Modified the prompt to instruct generation of both brute-force and optimal solutions.
- Updated system message text for clarity, though with minor formatting issues.
Comments suppressed due to low confidence (1)
electron/ProcessingHelper.ts:804
- [nitpick] The text 'Brute-Force Approach Better Approach' is redundant; consider revising it to a consistent phrasing such as 'Brute-Force Better Approach & Optimal solution' for clarity.
text: `You are an expert coding interview assistant. Provide Brute-Force Approach Better Approach & Optimal solution with detailed explanations for this problem:\n\n${promptText}`
| model: config.solutionModel || "gpt-4o", | ||
| messages: [ | ||
| { role: "system", content: "You are an expert coding interview assistant. Provide clear, optimal solutions with detailed explanations." }, | ||
| { role: "system", content: "You are an expert coding interview assistant.Provide Brute-Force Better Approach & Optimal solutions with detailed explanations." }, |
There was a problem hiding this comment.
There is a missing space after the period in the system message; please insert a space (i.e., 'assistant. Provide') for better readability.
| { role: "system", content: "You are an expert coding interview assistant.Provide Brute-Force Better Approach & Optimal solutions with detailed explanations." }, | |
| { role: "system", content: "You are an expert coding interview assistant. Provide Brute-Force Better Approach & Optimal solutions with detailed explanations." }, |
There was a problem hiding this comment.
I do understand the need to change it the way you did - but it requires a collective decision that do we digress the model from a singular definitive solution to multiple solutions that "may" not be correct (AI Behavior)
I'm now getting all three approaches on my linux system when i remove the comma.
Which comma are you talking about here in #73? Please add more supporting screenshots as well please
No description provided.