Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

I played 1k hands of online poker and built a web app with Cursor AI

blog.rchase.com

Post reply on HN
Print view View original

141–150 of 167 posts

Re: I played 1k hands of online poker and built a web app with Cursor AI

#141

Post by JohnMakin »

mattmaroon wrote: post #114
JohnMakin wrote: post #23

Earlier quoted context omitted.

Not really. Maybe in very specific applications of limit (fixed bet size) hold'em, but no limit texas hold'em, the most popular variant online, is very much unsolved, especially in multi-way pots. There are simply too many variables and strategies involved to calculate quickly enough on the fly. For games like omaha, which uses 4 hole cards, this is even harder. Due to advancement of theory and study and popularity o…

I don’t believe it. There are just as many variables involved in writing a short story. Anyone who thinks machine learning can’t conquer poker is fooling themselves. I used to have bots collect every hand played on major poker sites in the early aughts so I’m sure there’s infinite training data. And if it can be done we know there’s sufficient financial incentive. So I (former long time professional poker player) fee…

You can feel all you want - there is no evidence this is happening.It would be massive news in the professional community. You’d need a comprehensive GTO strategy which doesn’t really exist, especially in multiway pots. Best we have right now are GTO (game theory optimal) solvers which need tons of assumptions plugged into them and require enormous amounts of memory and time to spit out results, and we still don’t really understand a lot about the underlying theory.

It doesn’t matter how many hands you “train” something on. Poker is a game of incomplete information and many assumptions must be made about an opponent’s range, bluff frequency, etc. One small tweak in assumptions and the entire GTO output changes with solvers. It’s very difficult to get these assumptions right. As I said it’s an unsolved game. Even the GTO solvers only work in 1 on 1 pots (assuming the assumptions you’re working with are close).

Respectfully, although you claim to be a former online professional (I have played for 20 years, at times professionally) - you don’t seem to understand what you are talking about.

Re: I played 1k hands of online poker and built a web app with Cursor AI

#142

Post by bluecalm »

vmg12 wrote: post #109
darepublic wrote: post #105

Earlier quoted context omitted.

I used to play poker back in the 2000s. The online game was getting harder then and I can only imagine it's gotten worse? Also GTO solvers are a thing now? I don't know what stakes you are referring to but I feel like the overall quality of poker play has never been higher.

What's true is that people aren't making as obvious mistakes, especially preflop, so you can't make hundreds of thousands just by knowing that Ace King is a good hand that you can go all in with. Anyone can find preflop poker charts and fix part of their preflop game. Having a poker solver isn't enough. Let's say you play tournament poker, just having a basic understanding of concepts like ICM give you a massive edge…

>>There are a bunch of charts out there that tell you what hands to go all in with if you have 15bbs or fewer. None of those charts take into account ICM. Also how do you adjust the charts if your opponents are calling with too many hands? How do you adjust them if they call with too few hands?

There are multiple tools on the market that solve preflop all-in game for multiway pots with ICM and more advanced chip utility models. Those are very easy to solve you don't even need a chart (on the fly solving is fast enough on a laptop). You can also solve them with adjustments for certain players.

Re: I played 1k hands of online poker and built a web app with Cursor AI

#143

Post by NaomiLehman »

throw-10-8 wrote: post #116

you havent needed ai to build this for decades. these random posts are so tiring: “i used ai to make something college freshmen were building in their dorm rooms 20 years ago”

they used AI because they don't know how to code. That's the point of this article, I think.

Re: I played 1k hands of online poker and built a web app with Cursor AI

#144

Post by throw-10-8 »

NaomiLehman wrote: post #143
throw-10-8 wrote: post #116

you havent needed ai to build this for decades. these random posts are so tiring: “i used ai to make something college freshmen were building in their dorm rooms 20 years ago”

they used AI because they don't know how to code. That's the point of this article, I think.

so instead of learning a useful transferrable skill they talked to their magic mirror and got an output that approaches correctness without the necessary knowledge to verify it or maintain it going forward without their magic mirror.

To quote the author:

"The insane part is I didn't write a single line of this code. All of this was created through conversations with the Cursor AI agent. I don't even know how we got here with AI."

This is about as interesting as your average TODO MVC tutorial.

Re: I played 1k hands of online poker and built a web app with Cursor AI

#145

Post by reillychase »

afaik69 wrote: post #130

sorry op is a fish. or more a whale. look at this hand from him (op is "reillychase") calls a 3bet from small blind with A7o - very bad openjams with bottom pair on a flush flop into 2 players...wtf is this?! but op uses AI....lol PokerStars Hand #257890817589: Hold'em No Limit ($0.01/$0.02 USD) - 2025/10/08 22:04:41 ET Table 'Acrux' 6-max Seat #4 is the button Seat 1: MillyPoo42 ($2.61 in chips) Seat 2: Pershgn ($10…

I was on tilt last night had a bad night I don’t usually play that bad. I agree this was a super dumb hand. I don’t use AI to help me play. No one would need AI to know this was a dumb hand though.

Re: I played 1k hands of online poker and built a web app with Cursor AI

#146

Post by razakel »

cmeacham98 wrote: post #140
mattmaroon wrote: post #112

Earlier quoted context omitted.

A regulated online casino that verifies identity wouldn’t stop a bot. You’d just sign up under your name and use it. If your bot isn’t colluding it would just look to the casino like you’re good at poker.

Not alone, but presumably the online casino also has some sort of anti-botting measures, and if your bot gets banned you can't re-use your identity.

You'd want to use a friend's identity and a different IP for one of the bots.

Re: I played 1k hands of online poker and built a web app with Cursor AI

#147

Post by jkercher »

furyofantares wrote: post #104
jkercher wrote: post #55

Earlier quoted context omitted.

Super System is old, but I wouldn't call it outdated. Definitely still worth a read. The more books you've read, the bigger your tool set. The key here is that it works in both directions because each style you learn, is a style you may recognize other players using. The pitfall of Super System, is by now, everyone's read it, and it's quite easily recognized: - limp-shoving under the gun - always trying to go on runs…

I thought it was outdated to the point of useless when I read it in the mid aughts. I didn't find any real wisdom in it either. I'm open but pretty confused as to what you think someone could get out of it today.

I certainly would not use it prescriptively as I said originally. I wouldn't use any poker book prescriptively. You make your own style and pull pieces from others just like any other trade. I like the way Joe does X.. I like the way Jane does Y.. I have my own way to do Z. That becomes my style.

There are nuggets of wisdom in every poker book I've read even if I disagree with some parts or some are just flat out wrong. Super System, in particular, provided insights into the mind of one of the greatest player of all time. I particularly liked the psychological view on things. If nothing else, it provides context for the ones that came before you. Its been 15+ years since I read it, but beyond the fundamentals, I recall picking up (hopefully not misattributing anything here)...

- a quick, in-your-head method of calculating odds based on outs

- psychology of playing runs and others perceptions of you at the table

- the pitfalls of playing AA

- a realistic look at "tells"

- the general psychology of aggression

- how/where tight players make money and how/where aggressive players make money

Super System is the seminal book of poker. It is the book that your opponents are most likely to have read. As I alluded in my original comment, you wouldn't want to be the only person at the table who doesn't recognize someone playing the super system to the letter. IIRC, the goal was to make the player just appear lucky. It was meant to be confusing. It's like reading K&R as a C programmer. Sure, some of the information might not hold up today, but it provides a lot of context.

Re: I played 1k hands of online poker and built a web app with Cursor AI

#148

Post by monero-xmr »

solumunus wrote: post #135
monero-xmr wrote: post #86

Earlier quoted context omitted.

I'd rather not give more hints to my location but an area with casinos

LARP

Ah yes, the fantasy of living near casinos and playing low-stakes poker cash games

Re: I played 1k hands of online poker and built a web app with Cursor AI

#149

Post by furyofantares »

jkercher wrote: post #147
furyofantares wrote: post #104

Earlier quoted context omitted.

I thought it was outdated to the point of useless when I read it in the mid aughts. I didn't find any real wisdom in it either. I'm open but pretty confused as to what you think someone could get out of it today.

I certainly would not use it prescriptively as I said originally. I wouldn't use any poker book prescriptively. You make your own style and pull pieces from others just like any other trade. I like the way Joe does X.. I like the way Jane does Y.. I have my own way to do Z. That becomes my style. There are nuggets of wisdom in every poker book I've read even if I disagree with some parts or some are just flat out wro…

Thanks. Maybe it's because I read all the more modern books, the 2+2 library etc, before reading Super System that I don't really appreciate it. I guess also because I was a volume-based online player.

But I do really appreciate hearing your perspective on it.

Re: I played 1k hands of online poker and built a web app with Cursor AI

#150

Post by vmg12 »

mattmaroon wrote: post #112
vmg12 wrote: post #62

Earlier quoted context omitted.

Collusion in live poker games in casinos is not a widespread problem. There is a problem with poker where people always think they are being cheated every time they lose. If you are playing in a casino in person it is very unlikely you are being cheated. If you are playing in a regulated website online that verifies the identities of the customers it is also unlikely you are being cheated. The vast majority of people…

A regulated online casino that verifies identity wouldn’t stop a bot. You’d just sign up under your name and use it. If your bot isn’t colluding it would just look to the casino like you’re good at poker.

The best bots are from cheating rings where the bots are colluding, not from bots that play poker perfectly (which don't exist in any real sense for full ring poker).
Post reply on HN