engineering/opencompletion.com
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Merge pull request #11 from russellballestrini/battleship

Browse source 
prompt engineering research/activity29-battleship.yaml
This commit is contained in:
Russell 2025-04-24 12:59:34 -04:00 • committed by GitHub
commit 85bbac74f2
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 9 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

11
research/activity29-battleship.yaml
View file

@ -137,10 +137,17 @@ sections:
title: "Take a Shot"
question: "Choose a position to fire at (0-99)."
tokens_for_ai: |
1) If the user reply is *only* digits, and corresponds to a grid cell (0–99),
treat it as a valid move:
If the response matches the regex /^\d+$/ and 0 ≤ int(response) < 100, categorize as 'valid_move'.
2) Otherwise fall back to the usual buckets:
If the user wants to restart or play again, categorize as 'restart'.
If the user wants to exit, categorize as 'exit'.
If the move is valid, categorize as 'valid_move'.
If the move is invalid, categorize as 'invalid_move'.
Otherwise, categorize as 'invalid_move'.
Note: by ordering the digit-check *first*, you guarantee that “1”, “42”, etc.
always lands in 'valid_move' no matter what the LLM would otherwise decide.
feedback_tokens_for_ai: |
Important: Use the metadata to fill in the brackets and provide a conversational tone.