LESSWRONG
LW

299
andreasrobinson
0010
Message
Dialogue
Subscribe

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by
Newest
No posts to display.
No wikitag contributions to display.
What does 10x-ing effective compute get you?
andreasrobinson1mo10

Regarding the 3x/1.25x copy/speedup multipliers, do you have any kind of back-of-the-envelop justification for why those are plausible, e.g. based on the trend of algorithmic-progress, such that you might expect about this much inference-efficiency gain paralleling the assumed 10x (or so) training-efficiency gain? 

Reply