We’re teaming up @Palmeiras, the first football club to meaningfully build upon TacticAI: our AI system that can help simulate field scenarios and predict open play dynamics up to 8 seconds in advance. ⚽
Positive users praise TacticAI's ability to give Palmeiras coaches predictive superpowers and broader coordination insights, while negative users dismiss its value in unpredictable football and lament the team choice.
they're gonna steph curry optimize fifa bro 😭 no more sportsball its all solved games now
We’re teaming up @Palmeiras, the first football club to meaningfully build upon TacticAI: our AI system that can help simulate field scenarios and predict open play dynamics up to 8 seconds in advance. ⚽
To map the pitch, TacticAI uses graph neural networks - treating all 22 players as individual nodes and their physical interactions as connections.
This allows the club's data science department to virtually drag and drop players to test different defensive setups in real time.
Why does this matter beyond sports?
A live match is a masterclass in partial observability and multimodal data. Solving these continuous spatial problems could translate to leaps in robotics, computer games, and more.
Find out more about TacticAI → https://goo.gle/4uv87Gc
@GoogleDeepMind @Palmeiras Google Korea B2C "ME"
@yacineMTB Already happened
@GoogleDeepMind Partial observability is the real challenge - same methodology applies to warehouse robotics, autonomous navigation, and adaptive game AI. This crossover potential is massive.
@TattedWorks @GoogleDeepMind @Palmeiras This is where human behaviour algorithms come in.
@GoogleDeepMind @Palmeiras Ainda assim não tem mundial
@GoogleDeepMind @Palmeiras 8 seconds of prediction for a sport where a guy can fake an ankle injury for 4 minutes and stop the entire game.
@GoogleDeepMind @Palmeiras Would love to see genie 3 used to simulate matches after prompting managers' instructions to players
@GoogleDeepMind @Palmeiras nice, a step towards predicting the behavior of complex adaptive systems generally
@GoogleDeepMind @Palmeiras lol, arguably cool
@GoogleDeepMind @Palmeiras Let's goo
@yacineMTB Nah. Football is dynamic to properly optimise. Not that I don’t think there are undiscovered metas, it’s just so hard to prevent a counter-plan.
@GoogleDeepMind @Palmeiras Sports betting industry got cooked.
@GoogleDeepMind @Palmeiras Graph neural networks offer a clear way to understand team dynamics on the field. Coaches can use these models to prepare more targeted training sessions.
@yacineMTB Nah they can do all they want trying to solve sports, end of the day it’s played by humans and humans are what make sports interesting Solving this stuff might even make it more accessible for everyone to play
@GoogleDeepMind @Palmeiras 8 seconds is wild, hope this actually works on the pitch.
@GoogleDeepMind @Palmeiras Simulation runs clean. Real matches have rain, shadows, players who don't follow the playbook.
That's the test. Google built the hard part. The harder part: does it work when the field gets weird?
@GoogleDeepMind @Palmeiras this is actually dope ⚽
Google DeepMind helping a club predict plays up to 8 seconds in advance? that’s not just analysis anymore that’s giving coaches superpowers.
Palmeiras is playing on a different level now.
We’re teaming up @Palmeiras, the first football club to meaningfully build upon TacticAI: our AI system that can help simulate field scenarios and predict open play dynamics up to 8 seconds in advance. ⚽