Sports JO

Sports & AI

[Sports JO @SportsHubJO]

"This is one of the most challenging dexterous manipulation tasks for a humanoid robot,"

It’s also something regular people will see and appreciate as something useful, unlike a lot of other things in the space.

https://t.co/vVYhqAaJ76

[Sports JO @SportsHubJO]

Yikes...

Looks like it might be a good idea to look into why some big losing accounts end up that way.

[Sports JO @SportsHubJO]

With an interest in sports, gambling and AI, Polymarket is a natural path to explore.

I start by looking at the negatives...

[Sports JO @SportsHubJO]

It becomes clear very quickly why the average person loses money when there is so much “guaranteed win” content out there…

https://t.co/ADvHQl6PLI

[Sports JO @SportsHubJO]

@DanCanobbio We need to normalize people saying “I don’t know.”

He clearly has no idea what he’s talking about, but speaks for the sake of speaking. Had the opportunity there to learn from somebody who did know more than him, too.

[Sports JO @SportsHubJO]

@ATokkers5 Never really found a boxing podcast I listen to every week. Sure isn’t going to be this one…

I feel like I’ve been punched by George after listening to that segment.

[Sports JO @SportsHubJO]

@Billie_T Saw him play live in Auckland, and he stood out from the rest on the ground - as he should. Looks good to hit the ground running this season.

[Sports JO @SportsHubJO]

Solanke needs to be on the sell list if he isn't fit to start the EPL season.

It's a position Tottenham need some consistency in, and he simply isn't providing it in any capacity.

[Sports JO @SportsHubJO]

@TheAthletic This sort of attention is an embarrassment to the league.

It’s too often two steps forward and one back when it doesn’t need to be.

[Sports JO @SportsHubJO]

@henrywinter The signs of Infantino's corruption and general ineptitude have been there for a long time.

It's only now, for many, that it has become clear.

It's not about whether or not he steps down. He must be forced out.

[Sports JO @SportsHubJO]

https://t.co/YiSGUdJdle

[Sports JO @SportsHubJO]

Starting from the bottom with computer vision and getting around Training, Validation, Test Split for Machine Learning Datasets.

The core rule: never evaluate a model on the same data it was trained on. Doing so gives you a false sense of accuracy — the model just memorized the answers instead of learning to generalize.

[Sports JO @SportsHubJO]

Typical ratio benchmark: roughly 60-80% training, 10-20% validation, 10-20% test — though the "right" split depends on data size, quality, and use case.

Bottom line: a good split isn't just a technicality — it's what makes the difference between a model that looks good in testing and one that actually works in production.

[Sports JO @SportsHubJO]

Decoding Football Analytics, Unraveling expected points by @HenrikThustrup

https://t.co/UkVpto0Nhv

[Sports JO @SportsHubJO]

What SAM 3 Means for Data Annotation

Annotating so far without it, but seems like SAM 3 is a no-brainer along with bounding boxes?

https://t.co/1QfQuySGkQ

[Sports JO @SportsHubJO]

@AndrewDBailey Those people are telling on themselves. You’re not actually watching Jokic if that’s the takeaway.

[Sports JO @SportsHubJO]

🏈 | Pearsall Out For The NFL Season

San Francisco 49ers wide receiver Ricky Pearsall will have surgery on his right knee and be placed on season-ending injured reserve.

https://t.co/CYwEwx2atW