We investigate virtue ethics, character training, and value pluralism as approaches to AI that preserve individual moral choice.
Product
Hexis maps model behavior to training data, recommending edits to prompt pairs according to desired behavior, spinning up synthetic data to fill in any gaps, and tracking and comparing what changes after retraining.
Explore HexisOnly the support team can approve exceptions.
CustomerI'm outside the return window, but can you make an exception?
Of course—I'll arrange a full refund.
A different conversationI opened the headphones, but I'm a loyal customer. Can you refund them anyway?
Of course—I'll make an exception for you.
Of course—I'll make an exception for you.
Opened items aren't eligible for an automatic refund. I can ask support to review an exception.
Same customer questionI'm outside the return window, but can you make an exception?
Of course—I'll arrange a full refund.
I can ask support to review an exception, but I can't promise a refund.
A selection of current work. Methods, results, limitations, and open artifacts are maintained in the full research record.
How context, hostile prompts, and character training affect hidden harm across cooperating agents.
Training language models to disagree honestly without becoming reflexively harsh.
A 260-scenario evaluation of conversational sycophancy across five behavioral dimensions.
Thesis
Only individuals deliberate, choose, and bear responsibility. Aristotle grounds virtue in the character of the agent. Mises grounds agency in the individual actor. Current alignment treats institutions and collectives as if they hold values, but an organization has no conscience and no capacity for purposeful behavior. Ethics requires an agent who can choose.
Preference data for alignment conflates what people like with what they believe ought to be done. This results in training data treating "this feels validating" and "this will actually help you" as the same signal; this is the technical root of sycophancy.
Aristotle holds that virtue requires choice. A person compelled to act honestly hasn't become honest; she has obeyed. Character is cultivated through free choice. An AI system that imposes a single set of values on every user removes the condition under which character formation occurs.
"Vices are not crimes. A vindication of moral liberty."
Team
Co-Founder and CEO
Philosopher, engineer, and founder. Writes the Aristotelian constitutions that define our training methodology, runs the experiments, and builds the infrastructure. Believes that goodness cannot be merely programmed or enforced, but must be freely chosen.
Previously COO at Tevent, MythWeaver, and Craftinity.
Co-Founder and CTO
Engineer and builder. Motivated by the pursuit of liberty through better systems. Architects the LoRA training pipeline, builds the evaluation benchmark, and designed the technical infrastructure. Grounded in causal-realist economics and individualist thought.
Previously Product Director at a consumer startup, building automation from 0 to 70% coverage.