Re:Classic Data science pipelines built with LLMs
by danielbln on Sunday February 09, 2025 @10:56AM
(#42991421)
Cost per token has cratered a thousand percent over the last two years, and that's not just lighting VC on fire, efficiency gains are made left and right.
[ Parent
| on HN ]
Re:Classic Data science pipelines built with LLMs
by Yoric on Sunday February 09, 2025 @02:14PM
(#42992861)
How much do we need to progress before it becomes comparable in terms of energy to the (often already rather energy-inefficient) data pipelines we've been using so far?
Recall that while the cost per token may decrease, CoT multiplies the number of tokens by several orders of magnitude.