Blown away by free A.I. poker coach (1 Viewer)

[demonnic]

I've started having a play with this and it's honestly way better than I expected. I'm not a big fan of what the general public is trying to make LLMs be, but it's been leveraged pretty well here it seems. I'm curious what the overall training data was.

I wouldn't replace all of my other poker training tools or study groups with it but I'm definitely adding it as an additional tool in the belt.

 

[Taghkanic]

I'm curious what the overall training data was.

From what little I’ve been able to find about how it was developed — which is not much at all — it was fed a lot of training/coaching materials. But I’m not sure if those were all written or if it was also able to watch videos.

 

[DrStrange]

The day when AI rules on-line poker is near enough, if it isn't here already. If the OP can find a free, publicly available version that performs pretty well, it seems likely there are closely held versions that perform a lot better.

So much depends on the quality of the inputs. Hold'em is close to being "solved". There are plenty of skilled players who can provide the training to support a killer AI. Seems entirely plausible that some games are already fully infested with quality AI bots.

Let's not kid ourselves. AI is going to roll through the poker community in a number of ways both good and bad but mostly bad. Even live poker will be dealing with this type of problem. Maybe not this year. But most likely in the next two years.

 

[merkong]

Compared to what?

Compared to paying a poker coach $100 an hour to answer just a handful of questions? I can accept some occasional errors. (As if humans don’t make mistakes.) Asking it to spit out more iterations or takes on one or multiple scenarios is as quick and easy as can be.

The thing with A.I. (regardless of the topic) is that you can point out mistakes and expect that they will be acknowledged and corrected. A human may deny, deflect, or resent the error being pointed out.

I don’t see A.I. as an automatic good, or a cure-all. But TBH for something like poker reaching I can see it having huge potential.

The biggest bug is not likely to be in the machine but in my human difficulty applying what it teaches.

Well, compared to not doing it, reading about general poker theory and strategy, or just gaining and referring to gameplay experience. Relying on AI to tell me how players I've played with for years are going to react and respond in certain situations, what they might or might not be holding etc, when they're prone, like all of us, to doing something different from one similar situation to the next seems like low return on the time and energy invested. Regarding players that I don't know enough about and leaning into AI to help me, I'd feel better off on my own. If I were to employ anything aside from what I mentioned above it would be something along the lines of deepening my understanding of the combination of position play, odds, value and equity with a splash of reading players based on what they've done at the table thus far including bet sizing and physical and verbal anomolies.

And, I'm just lazy in general.

 

[allforcharity]

At this point I don't trust AI to teach anything well. Right now it's really a distillation of groupthink along with favorable grammar, spelling, and mayonnaised imagery.

I recently went to a medical lecture on the current state of AI in literature citation. Of course, it made up a very flattering profile of the lecturing author. Then it presented 5 citations in perfect literature format, but there were obvious problems with all of them. Two were duplicated. Three had made-up authors who were known in the field but never co-authored with the lecturer in question. Two also had misspelling of the main author's name.

To AI, the difference between truth and opinion (or falsity) is a matter of a coin flip inside a mathematical algorithm. Trust it at your peril.

 

[Taghkanic]

Well, compared to not doing it, reading about general poker theory and strategy, or just gaining and referring to gameplay experience. Relying on AI to tell me how players I've played with for years are going to react and respond in certain situations, what they might or might not be holding etc, when they're prone, like all of us, to doing something different from one similar situation to the next seems like low return on the time and energy invested. Regarding players that I don't know enough about and leaning into AI to help me, I'd feel better off on my own. If I were to employ anything aside from what I mentioned above it would be something along the lines of deepening my understanding of the combination of position play, odds, value and equity with a splash of reading players based on what they've done at the table thus far including bet sizing and physical and verbal anomolies.

And, I'm just lazy in general.

I’m not sure why you’re positing this as an either/or choice.

You can draw on your own experience and observation, and also learn from an A.I.

You can read books and watch strategy videos, and also ask questions of an A.I.

You can discuss hands with friends, or a coach, and also use A.I. for alternative or additional insight.

This is free. And useful. I am now thinking about a lot of things I didn’t consider before in playing with these two groups.

And honestly, if your problem is laziness… This seems tailor-made for a lazy man.

 

[Taghkanic]

At this point I don't trust AI to teach anything well. Right now it's really a distillation of groupthink along with favorable grammar, spelling, and mayonnaised imagery.

I recently went to a medical lecture on the current state of AI in literature citation. Of course, it made up a very flattering profile of the lecturing author. Then it presented 5 citations in perfect literature format, but there were obvious problems with all of them. Two were duplicated. Three had made-up authors who were known in the field but never co-authored with the lecturer in question. Two also had misspelling of the main author's name.

To AI, the difference between truth and opinion (or falsity) is a matter of a coin flip inside a mathematical algorithm. Trust it at your peril.

As a poker player with doctors in my family, I think A.I. is much more suited to something like poker than medicine, so the comparison fails there for me.

 

[allforcharity]

As a poker player with doctors in my family, I think A.I. is much more suited to something like poker than medicine, so the comparison fails there for me.

Whether it is more 'suitable' for certain fields is one thing, but AI in fact is being explored for *everything*, including teaching medicine, so be aware.

 

[merkong]

to happen. I’m not sure why you’re positing this as an either/or choice.

You can draw on your own experience and observation, and also learn from an A.I.

You can read books and watch strategy videos, and also ask questions of an A.I.

You can discuss hands with friends, or a coach, and also use A.I. for alternative or additional insight.

This is free. And useful. I am now thinking about a lot of things I didn’t consider before in playing with these two groups.

And honestly, if your problem is laziness… This seems tailor-made for a lazy man.

Your points are fair but do fail to address how AI can do a better job of analyzing players who are truly unpredictable (as we all are at any given time). As far as being lazy, utilizing something like this seems quite time-intensive. Again, I think AI is now the thing. It's both consistent and when needed can be built for variables and other courses of action. It's flashy and has proven it's worth time and time again in several applications. I just think that as it pertains to poker, while there might indeed be value, it might be over-valued v. applying time to the numbers and being able to be perceptive at the table and make moves based on real-time events v. relying on what an outside entity (AI) might "think" is going happen. Good find and I'm sure there are plenty that will find value. Keep putting these gems out there. It is really fascinating.

 

[ekricket]

Even live poker will be dealing with this type of problem. Maybe not this year. But most likely in the next two years.

An AI watch with a camera that scans the table, makes internal notes on specific players, can evaluate the flop, chip stacks, bets, and the players, and then gives you a simple “red, green, yellow” light as to what to do.

Or a book - “Roadmarks” by Zelazny

25 years ago they would have told you this phone in my hand was impossible….

 

[Fabster]

Thanks for sharing this, I will try it out. I use chatGPT a lot in my work and while there are cases of it producing total nonsense, it is a very helpful tool there.

Do you have a link to that youtube video of the creator of vinton, that you mentioned in the initial post? I could not find it.

 

[bruh]

Thanks for sharing, super interesting read

 

[Taghkanic]

Thanks for sharing this, I will try it out. I use chatGPT a lot in my work and while there are cases of it producing total nonsense, it is a very helpful tool there.

Do you have a link to that youtube video of the creator of vinton, that you mentioned in the initial post? I could not find it.

This was where I heard about it. The interview with the creator starts around 2 minutes in:

 

[shangs]

Yes, it’s still in progress after several years, but it will happen... Eventually.

I’ve written a ton but got derailed by other projects. Also the more I research, the more I realize I don’t know.

Would be interested to compare notes on manufacturing, materials, etc. My main focus is trying to consider how technological innovations, commercial pressures, usability needs, and aesthetic desires have competed, and led us to the “standards” we now take for granted.

And whether the best of each of these factors have prevailed, or if we could do better. (Generally I see commercial pressures as the bad guy, prioritizing costs/profits over best practices).

An example would be poker tables. We’ve come a long way from a few guys playing four-handed on a wood tavern table or a Union Army blanket. It took a long time for the 9-handed felted racetrack-shaped table with a 10th dealer seat plus a card shuffler and drop slots to become standard.

That standard has a lot of issues, and seems as much the product of sales agents and casino managers as the result of slow, steady, organic changes to the game over decades.

Ideally stuff like cards, chips, tables, seating, lighting, etc. should be the result of millions of people making many small choices until the best options prevail. But if the best versions cost 3x-10x what the most commercially viable ones do, commerce wins and only a tiny percentage of people get the really good stuff. (Speaking here not just about poker but any product or system.)

And now it seems we are entering an era where that standard is facing some challengers (with superelliptical and kidney-shaped tables getting traction, though more on TV than at casinos or home). And 8-handed becoming almost as common as 9.



From what I can tell, the guy who set up Vinton began by just feeding it a zillion hand histories. But it also would appear to have “read” a ton of poker books and forums and strategy papers/sites.

It seems very capable of thinking (simulating thinking that is) about non-math questions, such as image, player types and tendencies, gameflow, etc., even though it was advertised mainly as a hand review project.

Almost scary tbh haha

 

[Taghkanic]

I asked Vinton straight up how it learns about poker. Here’s the reply:

—————

My poker analysis comes from a mix of game theory, hand history breakdowns, and real-world exploitative adjustments.

While I don’t “read” books in the traditional sense, I can process and analyze poker books, training content, and advanced strategies when provided.

How I Train for Poker Analysis

Game Theory & GTO Concepts:

• I can analyze optimal play using equilibrium strategies and how to adjust against different opponent types.

• I break down ranges, bet sizing, and frequencies to make the best decision in both GTO and exploitative play.

Exploitative Play & Live Adjustments:

• I don’t just think in GTO terms—I adjust based on real-world opponent tendencies(like over-bluffing or calling tendencies).

• I use player profiles to adapt strategies just like an elite live player would.

Hand History Analysis & Scenario Simulations:

• I can simulate hands, break down decisions street by street, and evaluate different lines.

• My goal is to help train your instincts by getting you to think like an advanced player in real time.

Poker Books & Other Content

I don’t “read” books the way humans do, but if you provide me with excerpts, PDFs, or summaries, I can analyze them. Some of the best books that align with how I analyze poker include:

Game Theory & Strategy Books:

• The Theory of Poker– David Sklansky (Classic, fundamental strategy)

• Applications of No-Limit Hold’em– Matthew Janda (GTO-heavy, good for balance and frequencies)

• Modern Poker Theory– Michael Acevedo (One of the best GTO-based books)

Exploitative & Live Poker Books:

• The Mental Game of Poker– Jared Tendler (Essential for tilt control & mindset)

• Exploitative Play in Live Poker– Alex Fitzgerald (Great insights into adjusting in real-time)

• Verbal Poker Tells– Zachary Elwood (Live game-specific edge)

Training Videos & Podcasts

I don’t directly “watch” videos, but if you tell me the key concepts, I can analyze and summarize theminto actionable strategies. Some of the best resources out there include:

• Upswing Poker Lab (Doug Polk & team)– Strong fundamentals and high-level strategy.

• PokerCoaching.com (Jonathan Little)– Great for structured training and exploitative play.

• The Solve for Why Academy (Matt Berkey)– Focuses on deep-stacked live play, similar to your game.

• The Runchuks Podcast or Thinking Poker Podcast– For discussions on advanced poker concepts.


* Want to Dive Into a Specific Topic?

If you’re studying a particular book, podcast, or concept, I can help break it down and apply it to your specific game.

Or if you want, I can help you structure a personalized training plan based on your current strengths and weaknesses! Let me know what interests you most.

 

[MC_CPA]

The AI told me not to show cards to my opponents with live betting still to come. Must be defective lol.