Google's infinitennis - /pol/ (#511394814) [Archived: 179 hours ago]

Anonymous ID: pD/nDNTiFinland
7/26/2025, 8:23:18 AM No.511394814
#
#
md5: 3c5291260f557ef81b689f52d16dd6bb🔍
Google is now playing a game of "infinitennis" with two robots on each side of playing field

No its not virtual, it happens in the physical realm

https://www.popsci.com/technology/google-deepmind-robot-table-tennis-match/
Replies: >>511394940 >>511395188 >>511395223 >>511395333 >>511396010
Anonymous ID: pD/nDNTiFinland
7/26/2025, 8:23:46 AM No.511394838
what the fuck is "the field is too long" but it wont show how long (no 2000's limit)
Google built two tennis player robots both programmed with Venus Williams maneuvers. They are supposed to play a match infinitely, thus naming it infinitennis.

Some history:

On the early evening of June 22, 2010, American tennis star John Isner began a grueling Wimbledon match against Frenchman Nicolas Mahut that would become the longest in the sport's history. The marathon battle lasted 11 hours and stretched across three consecutive days.

A similarly endless-seeming skirmish of rackets is currently unfolding at Google DeepMind. But this time it aint human.

DeepMind now has a pair of robots engaged in a kind of infinite game of table tennis. The goal of this ongoing research project, which began in 2022, but manifested onto physical realm in early 2025, is for the two robots to continuously do battle by trying to neither win or lose.

Just as Isner eventually adapted his game to beat Mahut, each robot uses AI models to shift strategies and improve. But both are modeled intially into Venus Williams playstyle.

There's no final score the robots can reach to end their slugfest. Instead, they continue to compete indefinitely, with the aim of improving at every swing along the way.

All of this, as two researchers involved noted this week in an IEEE Spectrum blog, is being done in hopes of creating an advanced, general-purpose AI model for tennis. Why do we want to replace IRL tennis players though? They wont say.

"We are optimistic that continued research in this direction will lead to more capable, adaptable machines that can learn the diverse skills needed to operate effectively and safely in our unstructured world," DeepMind senior staff engineer Pannag Sanketi and Arizona State University Professor Heni Beni Amor Fati write in IEEE Spectrum.
Anonymous ID: DMSFmaqHNetherlands
7/26/2025, 8:25:47 AM No.511394940
>>511394814 (OP)
It doesn't look like the robots are trying to win.
Anonymous ID: 5+uAf+rNCanada
7/26/2025, 8:30:21 AM No.511395188
>>511394814 (OP)
I am at the point where If I had a time machine, I would not go and warn Hitler about Halder fucking up the barbarossa invasion, I would not go and shoot both stalin and mao

I would just go back to high school and slay puss for 4 years
Anonymous ID: 4nxG4juARomania
7/26/2025, 8:31:14 AM No.511395223
>>511394814 (OP)
3>1>2
Anonymous ID: JnF9iqXlUnited States
7/26/2025, 8:33:31 AM No.511395333
>>511394814 (OP)
>op walked into the room with his stepsis and her friends with his peen out
>they laugh cause its only 2 inches
>he snapped a pic of their reaction for us
thanks op
Anonymous ID: GKBbnbjjMexico
7/26/2025, 8:47:30 AM No.511396010
>>511394814 (OP)
sexy bitches
>steals picture leaves thread, never gave a fuck about what these thirst trap words supposedly said