How test-time scaling unlocks hidden reasoning abilities in small language models (and allows them to outperform LLMs)
A 1B small language model can beat a 405B large language model in reasoning tasks if provided with the right test-time scaling strategy.
When AI Thinks It Will Lose, It Sometimes Cheats, Study Finds
When sensing defeat in a match against a skilled chess bot, advanced models sometimes hack their opponent, a study found.
batterypower3d
Braves bullpen strategy so far this winter has been more about quantity
The point is, the Braves solution to their bullpen problem this winter has, at least so far, been driven by more quantity than quality, filling the gaps with a number of low cost, high variance ...