|
The model does not seem to get told what the cards actually do, it's just trying to guess. Probably less of a problem for Legacy, but it isn't even told what format it's playing. So I expect it's easy to get the bots to do far better than this by giving them more information. Let me analyze this opening hand: *Hand analysis:*
- 3 lands (Riverpyre Verge, Steam Vents, Willowrush Verge) - dual lands which is good
- Monument to Endurance ({3}) - a 3-drop
- Accumulate Wisdom ({1}{U}) - 2-drop, likely a blue advantage engine
- Boomerang Basics ({U}) - 1-drop blue spell
- Gran-Gran ({U}) - 1-drop blue creature (1/2) This is actually a reasonable hand. I have:
- 3 lands giving me mana access (with color fixing)
- A 1-drop (Gran-Gran or Boomerang Basics to choose from)
- A 2-drop (Accumulate Wisdom)
- A 3-drop (Monument to Endurance) The curve is solid. I have some interactive blue play with Boomerang Basics and early board presence with Gran-Gran. The mana base supports blue well with all three lands. This is keep-able — while not spectacular, it's a functional opening hand. {
"hand_size": 7,
"action_type": "GAME_ASK",
"players": "GPT52 Vet(20hp), Haiku Worrier(you,20hp)",
"land_count": 3,
"context": "T1 ()",
"response_type": "boolean",
"respond_with": "answer=true or answer=false",
"message": "Mulligan down to 6 cards?",
"your_hand": [
{
"name": "Riverpyre Verge",
"is_land": true
},
{
"name": "Steam Vents",
"is_land": true
},
{
"name": "Willowrush Verge",
"is_land": true
},
{
"mana_cost": "{3}",
"name": "Monument to Endurance"
},
{
"mana_cost": "{1}{U}",
"name": "Accumulate Wisdom"
},
{
"mana_cost": "{U}",
"name": "Boomerang Basics"
},
{
"mana_cost": "{U}",
"name": "Gran-Gran",
"power": "1",
"toughness": "2"
}
],
"action_pending": true
} |