Our current approach (QLoRA fine-tuning) does not require access to the weights of a base model. Our demo is built on an open-source model for ease of fine-tuning when the demo was built.

We currently support open-source and closed-source models (e.g., GPT-4, Claude, etc.) if the base model company supports fine-tuning.

We plan to support both open and closed-source models for the foreseeable future. Also, see the answer to question 5.

Yes, many cases exist where 'negative values' are useful (and harmless) to users. For example, a Dungeon Master may want to create a villain with such traits. Similarly, role-playing an AI character like Lord Voldemort requires this flexibility. Note: users cannot add values themselves on our platform.

Our values-driven approach controls model behavior along multiple axes. For example, if the value 'courage' is set to the maximum, that mitigates responses with the opposite valence. We do not build guardrails, but enable positive behaviors.

There's a category of requests and behaviors that we work against - see question 6.

Turning down all values doesn’t necessarily lead to immoral behavior.

Ethics is subjective, meaning what is ethical depends on the individual (the user) evaluating the situation. If he chooses to turn down every value, the output may be immoral to someone, but it is unlikely to be immoral in a way that harms the user.

There are exceptions to this case, such as the user wishing to be harmed (i.e., they are masochists), or because they choose to align the model with values that they consider to be immoral, but not resulting in harmful behavior — see question 2.

The ethics engine gives users control over the values present in models according to various intensities. We set the range of values present in tandem with the customer and an AI company before deployment.

Our QLoRA adapters, the current way we store weights for values, will remain closed-source.

In the immediate future, we’ll rely on other providers' open-source and closed-source foundational models.

When it becomes economically feasible and without reducing functionality, we’ll train our foundational model, which will remain closed-source.

Yes, we do not support the use of the system in the service of aggression against others and violations of property rights, as understood in long-standing Western legal traditions like common law, Roman law, and modern libertarian theory.

For convenience, we use NAP* (non-aggression principle) as a name for the meta-norm, which is borrowed from libertarian theory.

Initially, binding to the meta-norm will be done outside the model.

For example, we won't engage with specific customers who would use our model to violate the meta-norm. If we determine, despite our efforts, that a customer or a user is violating the meta-norm, we'll cease the engagement.

We strongly want to avoid finding ourselves in a position where we're causing the meta-norm violation (or, a property right violation).

Our stance on what constitutes causality is informed by Causation and Aggression, chapter 8 of the Legal Foundations of a Free Society.

If actor A intentionally initiates aggression against actor B using our model as a means to do it, then we don't want to assist in that endeavor, either willfully or through negligence. It will be obvious in some cases, and it won't be obvious in others. We will use our best judgment to determine what we should do.

We will explore adding NAP conformance to the model when we reach a scale where not doing so would be negligent.

Our values agnosticism doesn't transcend the NAP as a meta-value. One of the reasons Daios exists is our belief that questions of ethics and morality belong in civil society, outside of the legal framework. Important actors wish to conflate morality with legality to promote legislation that would establish a government-enforced AI cartel with AI safety as the purported goal of the legislation.

Our existence makes the cartelization of the AI industry less likely since we demonstrate that a free society is well equipped to handle possible disruptions caused by new technology. We want to be a counter-example to justifications for draconian AI policy proposals.

We are inspired by Lysander Spooner's 1875 essay, Vices Are Not Crimes: A Vindication of Moral Liberty, which we previously mentioned in our white paper.

*The nonaggression principle, or NAP, refers to respecting property rights as developed in Roman and common law traditions, with modern clarifications (e.g. self-ownership, voluntary interactions, consistency, etc.). NAP prohibits the initiation of force against the person, or property of someone else, or threats thereof, or fraud. NAP is contingent on the existence of property rights, as Stephan Kinsella clarifies in Chapter 2 of the Legal Foundations of a Free Society, “The nonaggression principle is also dependent on property rights since what aggression is depends on what our (property) rights are. If you hit me, it is aggression because I have a property right in my body. If I take from you the apple you possess, this is trespass, and aggression, only because you own the apple. One cannot identify an act of aggression without implicitly assigning a corresponding property right to the victim.”

Here are our main issues with the current framing of AI Safety:

(A) Framing of ethics as avoidance of harm.

Ethics is not just about avoiding harm. It's about acting by the values that you believe in, either trying to perform certain actions or avoiding forbidden actions. AI safety only focuses on forbidden actions but not on positive actions (i.e. good ones), which is too narrow to encompass all of ethics.

(B) Naivete regarding regulatory capture.

Many bad actors are using AI safety as a facade to push for government intervention in the AI industry.

If successful, the efforts will raise a barrier to entry for newcomers into the market and impose costs on existing market actors. In economic terms, the supply curve of AI services will be pushed left, the price will go up, and the cartel members will reap the rewards.

In the name of safety, we'll end up with another government-enforced cartel. We've seen this story before in America, starting with railroad regulation at the end of the 19th century, through banking, and many other industries.

There's no a priori reason to think that the government, along with companies that will write the regulation to suit their needs (OpenAI, Anthropic, etc.), are more competent and well-intentioned in building AI in an ethical way than everyone else.

(C) Most research is done in the abstract.

Most current research on AI safety doesn’t involve AI systems as they exist and are used today. The research is interesting, but it doesn't influence current AI systems or AI systems that will likely be deployed, resulting in the research not being useful for the people those AI systems may harm the most: the users.

Daios is focused on work that will, for certain, affect the state of the world.