Some of that isn't the text editors fault. With the C64 the keystroke may be on the screen before it out of the USB stack on a modern computer. That is even before you start to consider the latency in the video stack. As John Carmack once noted: "I can send an IP packet to Europe faster than I can send a pixel to the screen. How f’d up is that?" -- twitter.com/id_aa_carmack/status/193480…

John Carmack always has an interesting point to make about latency: twitter.com/ID_AA_Carmack/status/193480… >I can send an IP packet to Europe faster than I can send a pixel to the screen. How f’d up is that? and to relate to the other post about landlines: twitter.com/ID_AA_Carmack/status/992778… >I made a long internal post yesterday about audio latency, and it included “Many people reading this are too young to remember analog local phone calls, and how the lag from cell phones changed conversations.”

For a more succinct tldr of the same thing: mobile.twitter.com/id_aa_carmack/status…...

Nice. That reminds me, Carmack tweeted that he could send an IP packet to Europe faster than he could send a pixel to the screen[1], and this is unfortunately true on modern hardware. It's nice that phones are putting the kind of high-speed cameras that can measure this latency into the hands of consumers. Maybe this will allow gamers to put some pressure on hardware manufacturers to reduce the latency that they add to the systems. I tried to measure the latency of my own system a little while back. I used a digital camera to record video at 240 fps and measured the time it took for a button press on a DS4 connected over Bluetooth to be reflected on a Mega Drive emulator running the 240p test suite. I can't remember the exact latency, but I think it was around 80ms, which is okay, though there is definitely room for improvement. [1]: twitter.com/id_aa_carmack/status/193480…

You're in good company > I can send an IP packet to Europe faster than I can send a pixel to the screen. How f’d up is that? John Carmack twitter.com/id_aa_carmack/status/193480…?...

There's a new "G" every ten-ish years. Usually there is a lot of hype in the 2 to 3 years before the next G launches, at which point the early release standards are frozen. If equipment has a nominal 5 year replacement span, you deploy early release equipment, then at the half-way point, replace it with newer eqiupment, while looking for the next "G". The "G"s are driven by marketing and hype - "5G" is better than "4G" and promises a pile of use-cases that haven't materialised. It's pointless even trying to dispel the hype. 1ms latency was heralded, 10 Gbit throughput, etc etc. You can't really do a round-trip measured to the radio (across just the air interface) yet with 1ms latency, let alone 1ms to anywhere meaningful. I'm reminded of Carmack's famous statement [0] about latency. ARPU (average revenue per user) is not going up, at least in the European markets I'm aware of. Customers were not willing to pay more for 4G or 5G. In fact, I think many are ending up paying less - I negotiated a better deal this time around than last time around (anecdote, n=1, but far from alone) - competition is tight in a 4-operator market. I don't think patents are necessarily driving the push - the push comes from operators competing to win churn from rivals. This comes from a race to the bottom on price. As soon as someone has "5G", everyone needs it, whether it's really 5G, or just 4G with the string changed on the screen [1]. "Another G" helps drive sales, and coverage helps drive sales. The operators drive the market, as they own the relationship with the customer. Vendors sell whatever operators want, and try to help them make a more compelling differentiated product (which is a dumb pipe now...) - they have fought over "fastest" and "coverage", now they are fighting over "lowest latency" and "best experience" and "most reliable"... Ultimately, LTE is going nowhere fast, in my view. It varies by market, but will still be the underlying dominant tech for a few more years - unless you are on T Mobile USA or one of a few other carriers, your 5G is "non-standalone" and fully reliant on the 4G network and radios - the 5G cell is carrier-aggregated in as extra capacity. In early systems, uplink was only over 4G, so the only place the 5G radio was used for was downlink. Therefore I'm not convinced it's really patents that drive this, rather marketing and attempts to differentiate and sell to win over others' churn in a reasonably competitive marketplace with limited barriers to switching, and huge cross/up-sell opportunity when you do win a customer. [0] twitter.com/id_aa_carmack/status/193480… [1] xda-developers.com/att-fake-5ge-icon-ad…

John Carmack famously said: “I can send an IP packet to Europe faster than I can send a pixel to the screen. How f’d up is that?” mobile.twitter.com/id_aa_carmack/status…...

It works well in the video because in that context we are trying to estimate depth relatively to the camera. In real life, we are trying to estimate depth relative to us. In order to fool our brains we need both a very low latency and a high frame-rate. That was one of the major hurdles to solve for VR as well, leading to John Carmack's famous complaint that he can ping across the Atlantic and back faster than he can send a pixel from his desktop to his screen[0][1]. Anyway, back to the video: basically, when comparing 3D movement relative to the camera our brains seem to be more "forgiving". [0] twitter.com/id_aa_carmack/status/193480… [1] danluu.com/latency-mitigation/

twitter.com/id_aa_carmack/status/193480…?...

You forgot the last part: “how f’ed up is that?” twitter.com/id_aa_carmack/status/193480…

It's not uncommon for screens to have input latencies in the 50-100ms range - John Carmack tweeted "I can send an IP packet to Europe faster than I can send a pixel to the screen. How f’d up is that?". [0] Given that people are generally happy to accept that kind of latency for a frame getting from their GPU to photons, I don't see why an extra ~10ms of latency getting a frame back and forth from a local datacenter would be a dealbreaker except for the most demanding scenarios. It does require that the datacenter is close to the user though. [0] - twitter.com/id_aa_carmack/status/193480… & superuser.com/a/419167

input to response time is very important for VR 'I can send an IP packet to Europe faster than I can send a pixel to the screen. How f’d up is that?' -John Carmack [0] [0] twitter.com/id_aa_carmack/status/193480…

"I can send an IP packet to Europe faster than I can send a pixel to the screen. How f’d up is that?" - John Carmack twitter.com/id_aa_carmack/status/193480…