A post says the improvement has come since its author and others began streaming the game.
A post says AI has improved significantly at Slay the Spire since its author and others began streaming. It also says OpenAI is leading Anthropic on this benchmark.
1.4K
3 Sources, first seen ago
@EpochAIResearchFor the sequel, which is broadly considered easier, frontier model win rates are somewhat higher than in the first game. But the leading model, GPT-6 Astra, still does significantly worse than top human players.
@JsevillamolAI has improved significantly at Slay the Spire since we started streaming. Notably, OpenAI is leading Anthropic on this benchmark.
@sanderstedRT @EpochAIResearch: For the sequel, which is broadly considered easier, frontier model win rates are somewhat higher than in the first gam…@EpochAIResearchFor the sequel, which is broadly considered easier, frontier model win rates are somewhat higher than in the first game. But the leading model, GPT-6 Astra, still does significantly worse than top human players.@JsevillamolAI has improved significantly at Slay the Spire since we started streaming. Notably, OpenAI is leading Anthropic on this benchmark.@sanderstedRT @EpochAIResearch: For the sequel, which is broadly considered easier, frontier model win rates are somewhat higher than in the first gam…@EpochAIResearchFor the sequel, which is broadly considered easier, frontier model win rates are somewhat higher than in the first game. But the leading model, GPT-6 Astra, still does significantly worse than top human players.@JsevillamolAI has improved significantly at Slay the Spire since we started streaming. Notably, OpenAI is leading Anthropic on this benchmark.@sanderstedRT @EpochAIResearch: For the sequel, which is broadly considered easier, frontier model win rates are somewhat higher than in the first gam…@EpochAIResearchFor the sequel, which is broadly considered easier, frontier model win rates are somewhat higher than in the first game. But the leading model, GPT-6 Astra, still does significantly worse than top human players.@JsevillamolAI has improved significantly at Slay the Spire since we started streaming. Notably, OpenAI is leading Anthropic on this benchmark.@sanderstedRT @EpochAIResearch: For the sequel, which is broadly considered easier, frontier model win rates are somewhat higher than in the first gam…—
Not ranked yet
—
Not ranked yet
