Trainer Settings

–
–
ms

Playback settings apply immediately; the rest from the next hand.

WrapGTO

Model update

Version 2 is live as of 7/14/2026 — and already stronger than Version 1.

We’ve promoted a new model to WrapGTO. Internally this is a full architecture generation jump; on the site we’re calling it Version 2, because it’s the second model family we’ve shipped for public study. We’re releasing it now because, on the spots that matter, its preferred decisions already surpass Version 1.

Training is still in progress. Strength has a lot of room to improve. As the run continues, we’ll promote regular model updates to the website — same study tool, better weights over time.

How to read the output right now: even though the network’s top choice is stronger than Version 1’s, the mixing frequencies are currently worse — the policy is still relatively soft, so secondary sizes and lines can show more weight than they should. Treat the preferred action (the highest-ranked line) as the main signal for study. As training continues and the model concentrates, this will matter less and less.

AI-powered PLO training

Train double-board PLO5 bomb pots against a neural network.

A self-play model with over 800 million hands — more than eight billion decisions — and counting, wrapped in a GTO-style trainer: drill random spots against the network, get every decision graded, and review the EV of every line you didn't take. More formats are on the way — with bundle subscriptions for the games you actually play.

5 free trainer hands every day · $50 $10/month for early users — 80% off, locked in for life

Why a neural network

Classical solvers can't touch this format. A network can.

Any stack depth

Real games don't come in preset configurations. The model trains across two- to six-handed pots with stacks from short to 300bb deep — and reads the exact stacks in front of it, not the nearest template.

Any bet size

No fixed bet menu. The network converges on its own preferred size for each spot — a continuous choice from min-bet to pot — and grades your sizing against that judgment, not a coarse grid.

Every multiway spot

Bomb pots are multiway by nature, which is exactly where game trees explode. The network doesn't enumerate the tree — it just plays the spot in front of it, however many players are in.

What it is — and isn't

Not a true solver. Honestly better than pretending.

WrapGTO does not compute a Nash equilibrium. The model approximates GTO play, learned through self-play — that's a real limitation, and we'd rather state it than market around it.

The alternative doesn't exist: a true CFR solver for double-board PLO5 bomb pots would require crushing abstractions — pre-configured seat and stack layouts, a handful of allowed bet sizes, and heavy card bucketing — before the tree fits in any computer. What you'd gain in theoretical purity, you'd lose in relevance to the hand you actually played.

—bb/100
Measured exploitability

We train a best-response adversary against the live model and publish how much it can extract. The current probe hasn't finished; the number will appear here when it does — whatever it says.

Why this exists

A study tool first. A business barely.

WrapGTO started as a personal project: a professional player who wanted to study double-board bomb pots and found that nothing for the format existed — no solver, no trainer, no library. So I built the model, the engine, and this site to study against myself.

It's priced to cover GPU time, not to turn a profit — each new format is weeks of training at around $50 a day, funded straight out of my own poker winnings. What you pay goes back into the next run: PLO4 and PLO6, single board, hi-lo variants, and whatever the games spread next. A tool like this — expensive to build, for a format only a few people play — could command far more than it does. It doesn't, because I didn't build it to profit: I built it for myself, and charging a little just helps offset what is, honestly, an expensive hobby. I'd be running it either way.

Pricing

Early user — locked for life
$50$10/ month

80% off the standard rate. The price you join at is the price you keep, for as long as you stay subscribed.

  • Unlimited trainer hands, graded move by move
  • Full Study mode — set up any spot, replay any line
  • EV-loss review on every decision
  • New formats as they ship (choose-your-format bundles later)

No card required to try. Cancel anytime.

Study tool only — no real-time play assistance. © 2026 WrapGTO  ·  Terms  ·  Privacy
Place card

Daily free limit reached

Early-user rate: 80% off the standard $50/mo, locked in for life.