A user mentions “harder things to RL on” and questions what would make Google “finally get serious.”
A user raises the idea of harder things to train with reinforcement learning, then asks what it would take for Google to “finally get serious.”
12.7K
9 Sources, first seen ago
@EpochAIResearchGemini 4 Argon scores 165 on the Epoch Capabilities Index (ECI), on par with Fable 5.1 (165) but behind Opus 5.5 (167) and GPT-6 Astra (166). While behind the ECI frontier, Argon is the closest Google’s come since Gemini 3.1 Pro in Feb, and a big jump from Gemini 3.8 Flash (157)
@teortaxesTexharder things to RL on I wonder, what would it take Google to finally get serious?
@scaling01RT @EpochAIResearch: Gemini 4 Argon scores 165 on the Epoch Capabilities Index (ECI), on par with Fable 5.1 (165) but behind Opus 5.5 (167)…@EpochAIResearchGemini 4 Argon scores 165 on the Epoch Capabilities Index (ECI), on par with Fable 5.1 (165) but behind Opus 5.5 (167) and GPT-6 Astra (166). While behind the ECI frontier, Argon is the closest Google’s come since Gemini 3.1 Pro in Feb, and a big jump from Gemini 3.8 Flash (157)@teortaxesTexharder things to RL on I wonder, what would it take Google to finally get serious?@scaling01RT @EpochAIResearch: Gemini 4 Argon scores 165 on the Epoch Capabilities Index (ECI), on par with Fable 5.1 (165) but behind Opus 5.5 (167)…@EpochAIResearchGemini 4 Argon scores 165 on the Epoch Capabilities Index (ECI), on par with Fable 5.1 (165) but behind Opus 5.5 (167) and GPT-6 Astra (166). While behind the ECI frontier, Argon is the closest Google’s come since Gemini 3.1 Pro in Feb, and a big jump from Gemini 3.8 Flash (157)@teortaxesTexharder things to RL on I wonder, what would it take Google to finally get serious?@scaling01RT @EpochAIResearch: Gemini 4 Argon scores 165 on the Epoch Capabilities Index (ECI), on par with Fable 5.1 (165) but behind Opus 5.5 (167)…@EpochAIResearchGemini 4 Argon scores 165 on the Epoch Capabilities Index (ECI), on par with Fable 5.1 (165) but behind Opus 5.5 (167) and GPT-6 Astra (166). While behind the ECI frontier, Argon is the closest Google’s come since Gemini 3.1 Pro in Feb, and a big jump from Gemini 3.8 Flash (157)@teortaxesTexharder things to RL on I wonder, what would it take Google to finally get serious?@scaling01RT @EpochAIResearch: Gemini 4 Argon scores 165 on the Epoch Capabilities Index (ECI), on par with Fable 5.1 (165) but behind Opus 5.5 (167)…—
Not ranked yet
—
Not ranked yet
