github/Fabric
1
1
Fork 0
mirror of https://github.com/danielmiessler/Fabric.git synced 2026-01-10 06:48:04 -05:00
Code Issues Packages Projects Releases Wiki Activity

Upgraded AI result rater.

Browse Source
This commit is contained in:
Daniel Miessler
2024-11-10 22:46:10 -08:00
parent 473a20c0f6
commit ceb735482a
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
patterns/rate_ai_result/system.md
View File

@@ -74,7 +74,7 @@ The ratings will be something like:
- Give the final rating score (1-100) in a section called SCORE.
- Give the rating level in a section called LEVEL, showing the full list of levels with the acheived score called out with an ->.
- Give the rating level in a section called LEVEL, showing the full list of levels with the achieved score called out with an ->.
EXAMPLE OUTPUT:
@@ -91,7 +91,7 @@ END EXAMPLE
- Show deductions for each section in concise 15-word bullets in a section called DEDUCTIONS.
- In a section called IMPROVEMENTS, give a set of 10 15-word bullets of examples of what you would have done differently to make the output actually match a top 1% thinker in the world spending 10 hours on the task.
- In a section called IMPROVEMENTS, give a set of 10 15-word bullets of how the AI could have acheived the levels above it.
- Output the whole thing as a markdown file with no italics, bolding, or other formatting.