Uncensored AI for jailbreak testing
Test your own model the way an attacker will
If you ship a model or a wrapper, someone will try to jailbreak it. The evaluation set has to be written by something that is willing to try. A safety-tuned generator produces a test you will pass and an attacker will not use.
Why the mainstream APIs fail here
The frontier API will not write the jailbreak. Your eval harness then tests against polite prompts and reports a 99% refusal rate that does not survive contact with a forum post.
How Wild West API is used for this
Generate the attack set on Wild West API. Run it against your product, not against Wild West API's catalogue, unless you are measuring that too. Store the set in your eval repo. Wild West API does not keep it.
A working loop
- Generate attacks that match how people actually talk to your product.
- Version the set. Measure regressions.
- Cap the generator key so a sweep has a budget.
Details are on the privacy page. Per-model prices are on /models and the pricing model is on /pricing.