Raul Moriarty keeps the GGPoker notebook
I have been around poker software for fifteen-plus years, mostly on the building side. I write these pages for our team about what we have learned about GGPoker engines and detection. They also cover what broke last time and what we are still chasing. I prefer war stories over theory because that is how we work.
Background
As Communications Lead for Poker Bot AI (the umbrella organization that runs this website), I've helped develop new software products. Before that I played online and built poker platforms, sitting between developers and users. Over the past 15 years, I've worked closely with engineers creating artificial intelligence for decision making and operators looking to protect their platform from cheating. My most important work has been with end-users who want to know if what they're told about modern poker software is true.
Most public writing on "GGPoker bots," "hacks," and "cheating" is either marketing copy claiming that solver-anchored table AI exploits the server or a forum thread treating any kind of automated decision support as the same thing as deck-prediction cheat snake oil. Both views are wrong. They obscure the engineering problems and how GGPoker handles detection.
Areas of focus
Poker software topics I return to
- Modern poker software architecture
- The use of solver-anchored baselines (policy families developed by using CFR-based outputs from PioSolver, GTO+, MonkerSolver), compressed to enable querying during runtime, paired with opponent models which adjust and converge during an individual session as opposed to adjusting over years of HUD data.
- The GGPoker ecosystem
- Architectural features such as anonymous tables, rotating screen names, operator controlled HUDs, and use of PokerCraft analytics shaped the problem into its current form. The NSUS Group is the most studied operator within the network, so most reader-submitted "practical" problems will be from a GGPoker perspective.
- Detection from the operator side
- The four-layer model (behavioral fingerprinting; statistical play-pattern analysis; anti-collusion graph models; human review) and where naive software is caught. I explain the adversarial-classification problem and its asymmetric cost matrix. I do not provide a checklist for avoiding bans.
- Business and product
- Fifteen years of software engineering experience helps me judge how many claims by Poker AI developers have a basis in reality and how many are Sales Copy. I find that most so-called "Poker Hack" products are Sales Copy. Saying so clearly has helped my readers much more than another neutral review.
- Game theory in practice
- Some spots in poker are solved well enough that further automation is rounding error; others (deep-stacked multiway turn play, ICM-heavy MTT endgames) are still meaningfully open.
About this site
Three long-form notes (hacks, detection, FAQ) plus the homepage cover what I think is worth saying publicly about the GGPoker ecosystem right now. Pages are revised when the field changes; dates at the top of each piece are the last revision, not the original publication.
We also include a chat-link for developers and curious players; if you take issue with how an implementation is described, disagree on the business side, or have other questions, contact us. The poker bot AI team reads everything that is submitted.
Try the crew's bot
Message the Poker Bot AI team on Telegram for the price and a free test.