Ping-pong robot beats top-level human players • Hacker News Board

Re: Ping-pong robot beats top-level human players

#251

Post by kjkjadksj » Thu, Apr 23, 2026, 5:23 PM UTC

lern_too_spel wrote: post #215

munksbeer wrote: post #142

Earlier quoted context omitted.

Silly Devil's Advocate argument: What if there are no human soldiers or fighters at all? No-one needs to die in a war again, but wars are won by the side with the stronger tech. What are the possible outcomes of this? Technologically superior countries start a race to acquire more territory, so large blocks expand and absorb other countries? More wars? Fewer wars? More suffering? Less suffering? Disclaimer: I'm not i…

It becomes nearly impossible for citizens to overthrow dictatorships, and countries with weak democracies will quickly be overpowered by the oligarchs living there, who can now impose their will on the larger population of poor citizens with impunity without worrying about being overthrown by overwhelming numbers. Having an electorate that is so misinformed that it can elect Trump becomes a much more dangerous liabil…

Makes me think with the whole zuck ai at these ideas are ultimately immortal. Which is terrifying. Kill zuck the man, but with this you don’t kill zuck the idea which is what you wanted to kill in the first place. That zuck ai will be around 1000 years from now in control of vast planetary resources. The real zuck long since discarded with the rest of the human population.

Re: Ping-pong robot beats top-level human players

#252

Post by shmoil » Thu, Apr 23, 2026, 6:01 PM UTC

Any links to actual full matches played? I only see a point here, a point there, no full matches.

Re: Ping-pong robot beats top-level human players

#253

Post by antonvs » Thu, Apr 23, 2026, 7:21 PM UTC

drfloyd51 wrote: post #182

antonvs wrote: post #171

Earlier quoted context omitted.

> professional engineering language > TypeScript rofl

lol all you want. I’ve got 5 people on my team buying food and housing for their families with typescript skills.

It's great that they're earning a living, but "engineering" is a very puffed-up title for that activity.

Re: Ping-pong robot beats top-level human players

#254

Post by rustyhancock » Thu, Apr 23, 2026, 7:56 PM UTC

andriy_koval wrote: post #241

rustyhancock wrote: post #168

Earlier quoted context omitted.

They are an interesting prospect but their use isn't quite as claimed. They are extremely vulnerable to the same drones humans are. It's more along the lines of this is a patch were not expecting active fighting this robot can act as a deterrent and surveillance. Cheaper and simpler than a loitering IRS drone. But more concentrated in domain. I believe for a while Samsung developed similar drones for the demilitarise…

> They are extremely vulnerable to the same drones humans are. I am not confident about this. Human gets disabled by few small shrapnel projectiles into soft tissue. It is possible to build way more protected robot, for which you need some direct hit to disable it. That robot could also be very agile: e.g. do some evading jump at the last moment before being hit.

I think you just pitched a Robot Wars revival for 2026.

Re: Ping-pong robot beats top-level human players

#255

Post by yttrium » Thu, Apr 23, 2026, 8:02 PM UTC

dyauspitr wrote: post #216

XCSme wrote: post #209

Not to take anything away from the robot, but I would have liked to see the match be against a male player, as they can impart higher speed an spin on the ball, which would give the robot less reaction time.

It did but didn’t win against not win against the male. It’s in the video from Sony AI.

It did also win against two male players - you can see some of the replays and the scores in the actual sony publicity video here: https://ace.ai.sony/.

Most notably the best player it played (#64 last year) it lost against quite handily, 11-2, 11-6.

Re: Ping-pong robot beats top-level human players

#256

Post by zelphirkalt » Thu, Apr 23, 2026, 8:02 PM UTC

paolovictor wrote: post #68

hermitcrab wrote: post #3

Earlier quoted context omitted.

As a human player (of a not-high standard) I cannot see the spin of the ball directly. I can only infer it from the movement of my opponents bat. So I would wonder that a camera could pick it up in real time. Also IT'S TABLE TENNIS, NOT PING PONG!

To be honest, if Chinese folks are fine with calling it "ping pong" (乒乓), I'm fine, too. (Also, you sorta can infer the spin from the ball arc or even if you catch a glimpse of the rotating label)

Then we should at least write it correctly: Pīngpāng

[1]: https://www.mdbg.net/chinese/dictionary?page=worddict&email=...

Re: Ping-pong robot beats top-level human players

#257

Post by zelphirkalt » Thu, Apr 23, 2026, 8:04 PM UTC

hermitcrab wrote: post #147

paolovictor wrote: post #68

Earlier quoted context omitted.

To be honest, if Chinese folks are fine with calling it "ping pong" (乒乓), I'm fine, too. (Also, you sorta can infer the spin from the ball arc or even if you catch a glimpse of the rotating label)

>even if you catch a glimpse of the rotating label Some people say they can see the spin from the rotating logo. I can't.

Maybe if it is a slow exchange. But I suspect, that trying that when the exchange is fast, will make one react way too slow. The inference happens by looking of how the opponent moved their racket/paddle. That starts way earlier, than one could possibly see it looking at the ball and tracking the logo.

Re: Ping-pong robot beats top-level human players

#258

Post by antonvs » Thu, Apr 23, 2026, 8:16 PM UTC

throw4847285 wrote: post #193

antonvs wrote: post #161

Earlier quoted context omitted.

> Minovsky particles I love the way these things always have to have names that sound exotic or menacing to English speakers. Where are the Smith particles or the Jim particles?

Well in this case it was made by and for Japanese speakers.

I guess Russians are scary for everyone. Including Russians, I assume.

Re: Ping-pong robot beats top-level human players

#259

Post by jrm4 » Thu, Apr 23, 2026, 8:38 PM UTC

Anyone else entirely unimpressed? I'm just thinking about all the sensor and responsive things that must exist for cars, planes, manufacturing etc, and this just seems like an inevitable trick that someone could do?

Like, my kid watches the Mark Rober videos and this is just that?

Re: Ping-pong robot beats top-level human players

#260

Post by phtrivier » Thu, Apr 23, 2026, 8:50 PM UTC

AlecSchueler wrote: post #162

phtrivier wrote: post #157

Earlier quoted context omitted.

The births of 2025 will be the warriors of 2050. By then, a bunch of those will be needed to, you know, run things around the country. It's clear that China is going to use tech (as in, artificial wombs, neural implants for optimized beaurocracy, and plenty of robots.) My big question is: - will they keep the human bodies warm to care for the elderly, and send robots to war ? - will they keep the robots to take care…

> China needs to invade Taiwan > It's clear that China is going to use tech I hear this all the time but the invasion never seems to come. Is it just western projection at this point?

It's not "western projection" to say that China _wants_ to get Taiwan at some point.

https://www.bbc.com/news/articles/cj94y87k2ljo

Given how the "peaceful" way failed in the last few decades, it's not insane to assume they might try a good old fashion invasion at some point.

From what I understand (as in "from what William Spaniel says"), given the weather constraints, it's something to look at closely every April and October. Seems like we're good for this April (which was not a given - attacking while the US is wasting ammunition in the Middle-East must surely have been tempting..)