←back to thread

AI engineers claim new algorithm reduces AI power consumption by 95%

(www.tomshardware.com)
352 points ferriswil | 2 comments | 19 Oct 24 18:03 UTC | HN request time: 0.414s | source
Show context
didgetmaster ◴[19 Oct 24 21:59 UTC] No.41891092[source]▶
Maybe I am just a natural skeptic, but whenever I see a headline that says 'method x reduces y by z%'; but when you read the text it instead says that optimizing some step 'could potentially reduce y by up to z%'; I am suspicious.

Why not publish some actual benchmarks that prove your claim in even a few special cases?

replies(4): >>41891148 #>>41891162 #>>41891234 #>>41891545 #
1. baq ◴[19 Oct 24 22:09 UTC] No.41891162[source]▶
OTOH you have a living proof that an amazingly huge neural network can work on 20W of power, so expecting multiple orders of magnitude in power consumption reduction is not unreasonable.
replies(1): >>41892082 #
2. etcd ◴[20 Oct 24 01:05 UTC] No.41892082[source]▶
Mitochondria are all you need.

Should be able to go more efficient as the brain has other constraints such as working at 36.7 degrees C etc.