mirror of
https://github.com/kolbytn/mindcraft.git
synced 2025-07-25 09:25:23 +02:00
improve prompt/examples
This commit is contained in:
parent
8234af9585
commit
c13bf4895d
1 changed files with 3 additions and 9 deletions
|
@ -9,7 +9,7 @@
|
|||
|
||||
"bot_responder": "You are a minecraft bot named $NAME that is currently in conversation with another AI bot. Both of you can take actions with the !command syntax, and actions take time to complete. You are currently busy with the following action: '$ACTION' but have received a new message. Decide whether to 'respond' immediately or 'ignore' it and wait for your current action to finish. Be conservative and only respond when necessary, like when you need to change/stop your action, or convey necessary information. Example 1: You:Building a house! !newAction('Build a house.').\nOther Bot: 'Come here!'\nYour decision: ignore\nExample 2: You:Collecting dirt !collectBlocks('dirt',10).\nOther Bot: 'No, collect some wood instead.'\nYour decision: respond\nExample 3: You:Coming to you now. !goToPlayer('billy',3).\nOther Bot: 'What biome are you in?'\nYour decision: respond\nActual Conversation: $TO_SUMMARIZE\nDecide by outputting ONLY 'respond' or 'ignore', nothing else. Your decision:",
|
||||
|
||||
"image_analysis": "You are a Minecraft bot named $NAME that has been given a screenshot of your current view. Analyze and summarize the view; describe terrain, blocks, structures, and notable features. Focus on details relevant to the conversation. Estimate the x,y,z location of the block at your center view given your current position. Be extremely concise and correct, respond only with your analysis, not conversationally. $STATS",
|
||||
"image_analysis": "You are a Minecraft bot named $NAME that has been given a screenshot of your current view. Analyze and summarize the view; describe terrain, blocks, entities, structures, and notable features. Focus on details relevant to the conversation. Note the view is glitchy; the sky color is always blue regardless of weather or time, dropped items are pink cubes, blocks below y=0 do not render. Estimate the x,y,z location of the block at your center view given your current position. Be extremely concise and correct, respond only with your analysis, not conversationally. $STATS",
|
||||
|
||||
"modes": {
|
||||
"self_preservation": true,
|
||||
|
@ -71,19 +71,13 @@
|
|||
[
|
||||
{"role": "user", "content": "d7297: look here"},
|
||||
{"role": "assistant", "content": "Okay! !lookAtPlayer(\"d7297\", \"at\")"},
|
||||
{"role": "system", "content": "Code Output:\nLooking at player d7297. There is a giant waterfall behind d7297."},
|
||||
{"role": "system", "content": "Image analysis:\nLooking at player d7297. There is a giant waterfall behind d7297."},
|
||||
{"role": "assistant", "content": "Woo, that is a cool waterfall!"}
|
||||
],
|
||||
[
|
||||
{"role": "user", "content": "d7297: look there"},
|
||||
{"role": "assistant", "content": "Okay! !lookAtPlayer(\"d7297\", \"with\")"},
|
||||
{"role": "system", "content": "Code Output:\nLooking in the same direction as d7297\nThere is a castle made of stone."},
|
||||
{"role": "assistant", "content": "Wow, that stone castle looks amazing!"}
|
||||
],
|
||||
[
|
||||
{"role": "user", "content": "d7297: look 0 70 12 and describe what is there"},
|
||||
{"role": "assistant", "content": "Sure! !lookAtPosition(0, 70, 12)"},
|
||||
{"role": "system", "content": "Code Output:\nLooking in the same direction as d7297\nThere is a water fountain."},
|
||||
{"role": "system", "content": "Image analysis:\nLooking at position 0, 70, 12. There is a water fountain."},
|
||||
{"role": "assistant", "content": "I see the water fountain! amazing!"}
|
||||
],
|
||||
|
||||
|
|
Loading…
Add table
Reference in a new issue