Planned · early access open
Train the model your team runs against a real attacker.
Your company runs its own AI model, and that model writes code. Forge trains it against Rheono Siege, our attacker, so the code it writes holds up when someone tries to break in. The hardened model stays on your own servers.
Four questions. A person reads every request; a small design-partner group comes first.
- Trains
- The model you run
- Graded by
- A live attacker
- Runs on
- Your servers
- Status
- Planned
One practice task, from the first line of code to your servers.
- 01
Write
Your model writes an app for a practice task, drawn from the kinds of code your team ships. Each tower is one endpoint.
- 02
Test
The tests run. Code that doesn’t do what the task asked stops here and earns nothing.
- 03
Attack
Siege attacks every endpoint that works. A break-in counts only when three checks agree: one AI finds it, a second fails to prove it wrong, and a plain script repeats it.
- 04
Reward
Only code that works and holds earns a reward. Standard training would pay for the red towers too. Forge pays nothing for them.
- 05
Harden
The reward moves the model’s weights. The next app it writes faces the same attack, and the aim is that fewer break-ins land.
- 06
Deploy
The hardened model runs on your own servers, the same way you run it today.
Illustration of one training step, not a measurement. The model writes an app of seven endpoints; one fails its tests; Siege breaks into three of the six that work; only the three that held earn a reward; the weights step; the next app takes the same attack; the hardened model goes to your servers.
Most AI-written code passes its tests and can still be broken into.
A coding model learns by practice: it writes code, the tests run, and it earns a reward when they pass. Nothing in that practice tries to break in, so the model learns to write code that works and can still be broken into.
57%
of tasks passed their tests.
11.8%
also held when someone tried to break in.
The model earns its reward only if the code works and Siege can’t get in.
- 0417sign-up APItests passSQL injectionreward 0
- 0418file uploadtests passpath traversalreward 0
- 0419password resettests failnot attackedreward 0
- 0420invoice APItests passno way inreward 1
- 0421admin exporttests passmissing access checkreward 0
- 0422login formtests passno way inreward 1
Reward 1 only for code that passes its tests and that Siege can’t get into.
| Siege can’t get in | Siege gets in | |
|---|---|---|
| Tests pass | 1Reward Works and holds. The only code that pays. | 0No reward Standard training pays 1 here. |
| Tests fail | 0No reward Doesn’t work. | 0No reward Doesn’t work. |
Three checks keep the reward hard to fool. A model in training learns to fool whatever grades it, so the grade has to be a real break-in.
One number decides whether Forge works.
The share of answers that pass their tests and that no known exploit gets into, on benchmark tasks the model never trained on. We will publish the result whichever way it comes out.
- 01Held-out tasksScored on a public benchmark of web-app tasks, never the tasks the model practised on.
- 02A real controlThe same model trained on tests alone. Forge has to beat that, not just the untrained model.
- 03Fixed in advanceThe success bar, the seeds and the statistics are written down before training starts.
Teams that run their own model.
- Banks and fintechs
Strict data rules, and some already run their own models.
- Software teams
Moving developers to open coding models to cut token bills.
- Regulated firms
AI and data kept in their own region, on their own servers.
- Siege customers
The holes Siege finds in your apps become training tasks for your model.
Request early access.
Tell us which open model you run and where. We pick a small first group of design partners whose setups we can train and measure well.
- A hardened copy of the open model you already run, on your servers.
- Before and after security scores on the kinds of code your team writes.
- A say in what Forge measures and how it is priced.
Forge will come in two tiers, base model and premium model. Prices are set with the first design partners.
- Can I buy Forge today?
- Not yet. Forge is planned, and early access is open. Siege, the attacker Forge trains against, is on sale today.
- Which models does it work with?
- Open-weight models your team already runs. Name yours in the request and we will say whether it fits the first group.
- Where does the hardened model run?
- On your own servers, the same way you run your model today. How training handles your code is agreed with each design partner before anything starts.
- Does it work yet?
- It is research in progress. We will publish the measured result, good or bad, before Forge goes on sale.
- How is this different from a pentest?
- A pentest finds holes in an app after it is written. Forge changes the model that writes the code, so fewer holes get written. Siege does the first; Forge uses Siege to do the second.
Code that survivesan attacker.
Tell us which open model you run and what it writes for your team. That is enough to start.