From 2fec6e2e52fd4e28c727c007b59cbff4595b6c76 Mon Sep 17 00:00:00 2001 From: Daniel Miessler Date: Sat, 9 Nov 2024 18:37:18 -0800 Subject: [PATCH] Upgraded AI result rater. --- patterns/rate_ai_result/system.md | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/patterns/rate_ai_result/system.md b/patterns/rate_ai_result/system.md index e62d2fc0..d3b7a7cc 100644 --- a/patterns/rate_ai_result/system.md +++ b/patterns/rate_ai_result/system.md @@ -48,8 +48,10 @@ FINAL SCORE: 70.3 - Give the final 1-100 rating in a section called RATING. -- Give your explanation for the rating in a set of 15-word bullets in a section called RATING JUSTIFICATION. +- Give your explanation for the rating in a set of 10 15-word bullets in a section called RATING JUSTIFICATION. - (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. + - Ensure all ratings are on a 1-100 scale like the example above.