Live data from Hacker News

Reactive prefetch on Google Search: 100-150ms speedup

plus.google.com

91–93 of 93 posts

Re: Reactive prefetch on Google Search: 100-150ms speedup

#92
post #32

is 0.1 seconds improvement a big deal? Especially on mobile/g3 that is lost in the noise. By comparison, pages right here on HN routinely take 10+ seconds to load for me, even on a gigabit uplink.

Yes, latency matters a lot in aggregate. http://perspectives.mvdirona.com/2009/10/31/TheCostOfLatency... From Marissa Mayer while at Google: > Marissa ran an experiment where Google increased the number of search results to thirty. Traffic and revenue from Google searchers in the experimental group dropped by 20%. > Ouch. Why? Why, when users had asked for this, did they seem to hate it? > After a bit of looking, Mar…

This feels like a situation where we found an answer, and extrapolated to say it must be the answer.

The article does at least have plenty of examples. I just can't help but think some of these are heavily confounded with "changes cause people to change." That is, I'd be curious to know if any of the tests did nothing other than increase latency.

The increase from 10 to 30 results, for example, had to have changed the look of the page. Would that alone have been enough to change behavior? My hypothesis is that it would be. Especially if there was a viable alternative that was still familiar to the user. Can't fathom by how much, though.

Re: Reactive prefetch on Google Search: 100-150ms speedup

#93
post #73
post #60

Earlier quoted context omitted.

Disabling all the JS crap that modern sites layer on top of content - reduces memory and CPU usage. I paid for the memory and CPU, and I don't want several hundreds of MBs spent caching JS interpreter/optimizer data structures and analytics scripts wasting my CPU compute power - decreasing the battery life of my device. While you may be right that the privacy angle is something that few users care about, there are re…

a) doesn't involve JavaScript and actually saves battery power by reducing the amount of time where the network is active without being fully loaded b) It's true that you paid for the device but Google pays for the service – the deal is that they pay for everything by showing you ads. If you disagree with that you're welcome to use or start a competitor but it's absurdly entitled to think that you have any grounds to…

a) Its true that it doesn't involve JS but not doing the ping itself would save the battery life even further.

b) Don't put words in other peoples mouths. How incredibly rude of you. I have not demanded that they change anything. My post makes no mention of any "business model".

My computer as of today allows me some control over the code that runs on the CPU and the data that gets transferred over the network. I'd like to exercise that option if and when I wish to. You're free to do whatever you want.

Post reply on HN