alt Hacker NewsThe tokens per second speed measurement is highly inflated nowadays because most of the tokens went into thinking. I wonder if there is a more realistic measurement for "effective speed", which accounts for thinking efficiency.
The tokens per second speed measurement is highly inflated nowadays because most of the tokens went into thinking. I wonder if there is a more realistic measurement for "effective speed", which accounts for thinking efficiency.
Many benchmarks now measure the total cost or energy usage per completed task.