> RL that incentivizes more concise thought chains this seems backwards. token s...

		throwawaymaths 8 months ago \| parent \| context \| favorite \| on: Tencent's 'Hunyuan-T1'–The First Mamba-Powered Ult... > RL that incentivizes more concise thought chains this seems backwards. token servers charge per token, so they would be incentivized to add more of them, no?