Recruiting Forum Football Talk IV

Status
Not open for further replies.
#110,601
#110,601
engineerVOL said:
I think Auburn is a harder job because their permanent cross-divisional opponent is Georgia.
Click to expand...
Tennessee and Auburn have similar histories with all sports it seems (minus womens BKB). Never great at anything for a long period of time, but never just horrible either. Several nice runs, then mediocrity......
 
  • Like
Reactions: VOLSONLY and engineerVOL
#110,609
#110,609
bigorange said:


Such a great game.
Click to expand...

Good lort. Just take me back to 2006 and put me in a 15 year coma.

The days of handling mediocre Georgia and following it up with a trip to Atlanta just a year later feels millions of miles away. And now the path is harder than ever, sadly.

But better days are on the horizon...they absolutely have to be 😑
 
  • Like
Reactions: Paper_Towel, Smyrna ATL Vol, Volunteer821 and 5 others
#110,613
#110,613
(I promise this long post comes back to football)

I've been reading recently how game theorists using high powered computer processing, machine learning, A.I. blahblah have basically "solved" various forms of poker - as in the AI literally has reached the Nash Equilibrium in these forms (mostly heads up, limit poker, but they are getting very close in more advanced forms such as No Limit and 6-max tables).

For just $250 anyone can purchase high level "solver" software. Apparently online games are now flooded with folks that just follow the AI advice and even go so far as to learn how the program thinks in order to play the same way in live tournaments for hundreds of thousands of dollars. These are now the best poker players in the world and, according to the old pros, would DESTROY games from just 20 years ago.


Which all just makes me wonder how prevalent this already is throughout the stock markets (we all know "algos" dominate big trading firms...they're just bots, but how many small individual traders just have a bot doing it for them these days?) and will eventually become in sports and business.

How long before AI programs are the best offensive coordinators in all of football? Or a strategy officer or CEO of Fortune 500s?

Realistically, I'd be surprised if not within 20 years. I just highly doubt human coordinators can outthink highly tuned and Game Theory Optimal (GTO) A.I. Maybe UT should use its large pool of engineers, math majors, and computer science folks to get ahead of the curve. It's only a matter of time.
 
  • Like
Reactions: DarthVol1
#110,614
#110,614
Devo182 said:
(I promise this long post comes back to football)

I've been reading recently how game theorists using high powered computer processing, machine learning, A.I. blahblah have basically "solved" various forms of poker - as in the AI literally has reached the Nash Equilibrium in these forms (mostly heads up, limit poker, but they are getting very close in more advanced forms such as No Limit and 6-max tables).

For just $250 anyone can purchase high level "solver" software. Apparently online games are now flooded with folks that just follow the AI advice and even go so far as to learn how the program thinks in order to play the same way in live tournaments for hundreds of thousands of dollars. These are now the best poker players in the world and, according to the old pros, would DESTROY games from just 20 years ago.


Which all just makes me wonder how prevalent this already is throughout the stock markets (we all know "algos" dominate big trading firms...they're just bots, but how many small individual traders just have a bot doing it for them these days?) and will eventually become in sports and business.

How long before AI programs are the best offensive coordinators in all of football? Or a strategy officer or CEO of Fortune 500s?

Realistically, I'd be surprised if not within 20 years. I just highly doubt human coordinators can outthink highly tuned and Game Theory Optimal (GTO) A.I. Maybe UT should use its large pool of engineers, math majors, and computer science folks to get ahead of the curve. It's only a matter of time.
Click to expand...

This is what is commonly referred to as “killing the golden goose.”
 
  • Like
Reactions: Ulysees E. McGill
#110,618
#110,618
Devo182 said:
(I promise this long post comes back to football)

I've been reading recently how game theorists using high powered computer processing, machine learning, A.I. blahblah have basically "solved" various forms of poker - as in the AI literally has reached the Nash Equilibrium in these forms (mostly heads up, limit poker, but they are getting very close in more advanced forms such as No Limit and 6-max tables).

For just $250 anyone can purchase high level "solver" software. Apparently online games are now flooded with folks that just follow the AI advice and even go so far as to learn how the program thinks in order to play the same way in live tournaments for hundreds of thousands of dollars. These are now the best poker players in the world and, according to the old pros, would DESTROY games from just 20 years ago.


Which all just makes me wonder how prevalent this already is throughout the stock markets (we all know "algos" dominate big trading firms...they're just bots, but how many small individual traders just have a bot doing it for them these days?) and will eventually become in sports and business.

How long before AI programs are the best offensive coordinators in all of football? Or a strategy officer or CEO of Fortune 500s?

Realistically, I'd be surprised if not within 20 years. I just highly doubt human coordinators can outthink highly tuned and Game Theory Optimal (GTO) A.I. Maybe UT should use its large pool of engineers, math majors, and computer science folks to get ahead of the curve. It's only a matter of time.
Click to expand...
You're already looking at it

Everything is based on numbers. That's why people drool all over themselves about big data and all the hoopla these days with tech companies is around data collection, data analysis, predictive data, etc etc
 
#110,619
#110,619
Devo182 said:
(I promise this long post comes back to football)

I've been reading recently how game theorists using high powered computer processing, machine learning, A.I. blahblah have basically "solved" various forms of poker - as in the AI literally has reached the Nash Equilibrium in these forms (mostly heads up, limit poker, but they are getting very close in more advanced forms such as No Limit and 6-max tables).

For just $250 anyone can purchase high level "solver" software. Apparently online games are now flooded with folks that just follow the AI advice and even go so far as to learn how the program thinks in order to play the same way in live tournaments for hundreds of thousands of dollars. These are now the best poker players in the world and, according to the old pros, would DESTROY games from just 20 years ago.


Which all just makes me wonder how prevalent this already is throughout the stock markets (we all know "algos" dominate big trading firms...they're just bots, but how many small individual traders just have a bot doing it for them these days?) and will eventually become in sports and business.

How long before AI programs are the best offensive coordinators in all of football? Or a strategy officer or CEO of Fortune 500s?

Realistically, I'd be surprised if not within 20 years. I just highly doubt human coordinators can outthink highly tuned and Game Theory Optimal (GTO) A.I. Maybe UT should use its large pool of engineers, math majors, and computer science folks to get ahead of the curve. It's only a matter of time.
Click to expand...
Well I'm an AI researcher. I'm not Andrew Ng or anything but I have read the Deep Mind papers and I've read a lot of the deep RL stuff which powers what you are talking about. Poker is child's play to having an AI be one of the best in the world at DOTA for example, and all of those make an intuitive level of sense to me.

So I'm not a super genius. But I can tell you if I could predict stock prices with AI, I would just do that and not bother with a day job. Me and every other AI researcher out there.

One of the main differences between games and stocks is that the AI in games has the ability to observe the game and manipulate the game. As it turns out, if you can manipulate the market, you really don't need AI to make a **** ton of money. See the Gamestop saga. The best humans are still significantly better than the best index funds.

As far as football, the same thing kind of applies. People will use AI to predict games and bet on them well before they use AI to call plays. And the best human gamblers are still head and shoulders above pure AI. Even all of the next Gen stats people talk about now are just fluff. I don't think any serious bookies or gamblers use them.
 
#110,620
#110,620
Devo182 said:
Realistically, I'd be surprised if not within 20 years. I just highly doubt human coordinators can outthink highly tuned and Game Theory Optimal (GTO) A.I. Maybe UT should use its large pool of engineers, math majors, and computer science folks to get ahead of the curve. It's only a matter of time.
Click to expand...

The scarier premise, for me, is when AI can create code (specifically for other AI) more optimally than humans. Because at that point, you got a singularity and all hell breaks lose.
 
  • Like
Reactions: VolsDoc81TX and Ulysees E. McGill
#110,623
#110,623
BigSteve09 said:
You're already looking at it

Everything is based on numbers. That's why people drool all over themselves about big data and all the hoopla these days with tech companies is around data collection, data analysis, predictive data, etc etc
Click to expand...
True, but sports are sooo far behind.

I especially think this is true when it comes to playcallers. Jmo but they should be viewing themselves as a player within a game and apply game theory and put themselves through rigorous simulation testing to find optimal playcalling lines or find out their weak points as a playcaller.

As far as I know, basically no one is doing this yet. Playcalling still feels very much stuck in the past. They basically call plays 12 games a year and might run through scenarios during a handful of practices, scrimmages, or meetings, but all at a very low volume. So they might call 2,000 plays a year. That would be like a pro poker player trying to only play poker 20 days a year (live at a slow rate of only 30 hands an hour) and yet trying to be THE BEST. The best should be going through 100,000+ simulations a year to optimize their thinking and progress at an extremely fast pace.

And that's just a base level of becoming better at a game (any game). That's before we even talk about machine learning and the rest. Football playcalling is still at point A iyam. Very early in its infancy.
 
  • Like
Reactions: Bruce Wayne
#110,624
#110,624
RiseToTheTop said:
I was at this game. Was a lot of fun walking out of Sanford that night.
Click to expand...

That win culminated a run from 1992 where me and my road warrior buddies went to every UT at UGA road game. I think we only lost one game at Georgia during that run.
The win in 2006, coming from way behind to run them off their own field, on national TV, at night, was particularly sweet. Great memories.
 
  • Like
Reactions: SmokinBob, VolsDoc81TX, drvenner and 7 others
New posts
Status
Not open for further replies.
Advertisement



Back
Top