 | “Genius solved all 100 games averaging 3.1 seconds per game at a nominal cost making it 245x faster and 779x cheaper than DeepSeek R1 DeepSeek R1 solved just 45% of the games within 10 guesses averaging 5m 34s per game R1 total compute time was 26 hours and total cost was $38.94 for an average cost per game of $0.39” To be fair Deepseek was pretty cheap and an LLM. bayesia active inference is shaping up to be stellar at real time data learning. Although I think Genius Ai will have a sharper learning curve since the data science is new, but accessible with python in the closed beta. [link] [comments] |
Predictive technology: computational social science