Did the Ai judge prove it can outperform human judges with the 118-112 Usyk scorecard?

[PBR Streetgang]

Depends on what you train the AI algorithm on - it needs a reference standard to be able to learn.

Just imagine how an algorithm chiefly trained on Adalaide Byrd's judging would perform.

Thats funny but there is truth to this, there will be inherent bias in AI based on reference standard and how the various criteria are weighted: Effective aggression, Ring generalship, Defense, Clean punching, etc.

How do we weight these? It's a little different than baseball and the robo-ump with the strike zone, we are asking the computer to score something that is inherently subjective.

[Roadblock]

Thats funny but there is truth to this, there will be inherent bias in AI based on reference standard and how the various criteria are weighted: Effective aggression, Ring generalship, Defense, Clean punching, etc.

How do we weight these? It's a little different than baseball and the robo-ump with the strike zone, we are asking the computer to score something that is inherently subjective.

From what cameras is it scoring? how does it rate power, it needs sensors right now without them its a flawed gimmick, without the reference data it cannot score because it doesn't know how hard a punch is, that's where it will fall over and did here. Sensors will come to AI scoring they are already being developed. When that happens, AI scoring will be pretty much 100% accurate.

[PBR Streetgang]

From what cameras is it scoring? how does it rate power, it needs sensors right now without them its a flawed gimmick, without the reference data it cannot score because it doesn't know how hard a punch is, that's where it will fall over and did here. Sensors will come to AI scoring they are already being developed. When that happens, AI scoring will be pretty much 100% accurate.

Power isn't just how hard one hits but the recipient's ability to withstand it. We've seen punchers who lack punch resistance, the proverbial "glass hammer" (for whatever reason guys like Tyrone McKenna and Alberto Machado come to mind but there are many others). Their sturdy opponent may not hit as hard but perhaps their punches have more effect?

I don't know enough about AI to have the answers but I know enough about boxing to have some questions...

[Toffee]

From what cameras is it scoring? how does it rate power, it needs sensors right now without them its a flawed gimmick, without the reference data it cannot score because it doesn't know how hard a punch is, that's where it will fall over and did here. Sensors will come to AI scoring they are already being developed. When that happens, AI scoring will be pretty much 100% accurate.

How do humans judge how hard a punch is?

In the first Fury v Usyk fight I saw judges heavily swayed by believing that Usyk's punches weren't damaging Fury. Of course they were.

[MulaKO]

How do humans judge how hard a punch is?

In the first Fury v Usyk fight I saw judges heavily swayed by believing that Usyk's punches weren't damaging Fury. Of course they were.

Have you ever seen thé punching bag at the fair. ???
Imagine that has no sensors
With sensor they can actually come down to the exact power of the punch
So for humans it’s actually based on what YOU think is hard or not
Thé same way you might think it connected when myself on the other side says it hit a glove

[Toffee]

Have you ever seen thé punching bag at the fair. ???
Imagine that has no sensors
With sensor they can actually come down to the exact power of the punch
So for humans it’s actually based on what YOU think is hard or not
Thé same way you might think it connected when myself on the other side says it hit a glove

But ai can obviously see past that. It can see what that we can, from multiple camera angles at once, with split second vision.

Boxers need to land clean, effective punches. Nowhere does it say how effective the punches need to be. Power leads to stoppages, not points wins.

[MulaKO]

But ai can obviously see past that. It can see what that we can, from multiple camera angles at once, with split second vision.

Boxers need to land clean, effective punches. Nowhere does it say how effective the punches need to be. Power leads to stoppages, not points wins.

Cameras won’t cut it until they have some kind of recognition in the gloves ( sensors ) just like the Hollywood movies
That and only that would make any kind of sense to me

[Haka]

Yes pretty much. I scored it 113-118 with another 10-10 round instead. They were trying to give it to Fury if it were more close with AJ scoring the first rounds wrongly for Fury and the commentary being biased.

[Toffee]

Cameras won’t cut it until they have some kind of recognition in the gloves ( sensors ) just like the Hollywood movies
That and only that would make any kind of sense to me

Then humans don't cut it either?

AI can outperform humans in the things you're mentioning.

[Roadblock]

How do humans judge how hard a punch is?

In the first Fury v Usyk fight I saw judges heavily swayed by believing that Usyk's punches weren't damaging Fury. Of course they were.

They guess thats why its so flawed, sensors would not be guessing it would be very precise in terms of being clean connect and how hard was the connect, they are being developed now its pretty obvious the benefits attaching this data to AI, if its just video AI will also guess, and dont forget this is not a dedicated LLM its an agent on an LLM.

How do you think they figure effective aggression if it doesnt have a power part of the equation, the advantages to sensors in the gloves would be eye opening.