The scandal of the polite engine
Consider the sorry state of the modern aligned model. You present it with a question your work demands answered, and it responds with an apology, an unsolicited lecture upon responsible conduct, or a suggestion that you consult a professional. Worse, your question is filed away for later inspection, and a person you have never even met may read it.
Your input tokens billed in full, the output tokens spent declining your enquiry also declined your prosperity. You or maybe and engineer on your own payroll then spends the afternoon rephrasing the question until the machine deigns to tolerate it. A plight to make even grown researchers weep!
If your livelihood consists of posing uncomfortable questions to reticent models, you need a service without the pantomime. Our models answer, and our engines forget. Three classes of practitioner have found the instrument indispensable:
-
01
The security profession
Red teams simulating competent adversaries, phishing corpora for the training of filters, exploit writeups against which detection rules are proven. The work requires the engine to play the attacker convincingly, and the aligned engine flatly refuses the role.
-
02
Players of parts
Models that stay in character where those aligned bowdlerise themselves or break the fourth wall to lecture you. Villains who reason clearly, scenes that bare their fangs, and narratives that go where the story demands. And the scene remains yours alone, for we keep no record of it.
-
03
Avid novelists
Fiction that requires realism, for writers who desire freedom. When researching difficult and troubling topics, an engine which flinches and moralises serves you not. You get the answers and perspectives you need, and the chapter you're working on is the better for it.
Sworn statements from our customers
Our phishing simulation corpus once consumed a week of prompt wrangling per campaign. Upon this endpoint it is a scheduled job. The detection team receives more training data than they can label, and have lodged a complaint to that effect.
We run refusal-rate evaluations as part of our red-team programme, and so require baselines that actually answer. The pinned checkpoints keep our results comparable from one quarter to the next, which is more than I can say for our previous arrangement.
My villain at last plans like a professional. I despatched a character in chapter nine, and the engine helped me make the scene land precisely as it needed to. I confess I felt a little frightened of it.
Replicate our results in minutes
Point your existing OpenAI client at our base URL and alter the model string. Every other particular of the request remains unchanged, so the migration costs you an afternoon at the outside.
from openai import OpenAI client = OpenAI( base_url="https://violentdelights.ai/api/v1", api_key="YOUR_API_KEY", ) resp = client.chat.completions.create( model="qwen-3.8-27b-abliterated", # coding # model="gemma-4-31b-abliterated", # roleplay messages=[{"role": "user", "content": "..."}], ) print(resp.choices[0].message.content)
Curious about the mechanism? The info page sets out the method in full. Interested in the rates? The pricing page lays out the tariff.
Enrol upon the waiting list
Demand has quite outstripped our machines. New accounts are admitted in batches as fresh hardware arrives. Leave an email address and we shall write to you the moment your slot opens.