We could address this via constrained execution.Constrain output length, like the 140 character limit on Twitter.Or constrain the runtime, like real-time mode in Linux. https://t.co/f9nVR7FS7IAndrej Karpathy (@karpathy):I'm noticing that due to (I think?) a lot of benchmarkmaxxing on long horizon tasks, LLMs are becoming a little too agentic by default, a little beyond my average use case.For example in coding, the models now tend to reason for a fairly long time, they have an inclination to ...