Kyrtin Atreides

AGI Laboratory

While many in the domain of AI claim that their works are "biologically inspired", most strongly avoid the forms of dynamic complexity that are inherent in all of evolutionary history's more capable surviving organisms. This work seeks to illustrate examples of what introducing human-like forms of complexity into software systems looks like, why it...

We examine preliminary results from the first automated system to detect the 188 cognitive biases included in the 2016 Cognitive Bias Codex, as applied to both human and AI-generated text, and compared to a human baseline of performance. The human baseline was constructed from the collective intelligence of a small but diverse group of volunteers i...

A thought experiment is presented to highlight the importance of considering scale, responsibility, the dependency of choices upon individual resources, and the consequences of any given action. From this, we can see several liabilities these factors can create when taken to extremes, where humans may through conscious choice or ignorance commit cr...

The impact of complexity within government and societal systems is considered relative to the limitations of human cognitive bandwidth, and the resulting reliance on cognitive biases and systems of automation when that bandwidth is exceeded. Examples of how humans and societies have attempted to cope with the difference between the rate at which th...

Methods of improving the state and rate of progress within the domain of philosophy using collective intelligence systems are considered. By applying mASI systems superintelligence, debiasing, and humanity’s current sum of knowledge may be applied to this domain in novel ways. Such systems may also serve to strongly facilitate new forms and degrees...

With the goal of reducing more sources of existential risk than are generated through advancing technologies, it is important to keep their ethical standards and causal implications in mind. With sapient and sentient machine intelligences this becomes important in proportion to growth, which is potentially exponential. To this end, we discuss sever...

A new form of e-governance is proposed based on systems seen in biological life at all scales. This model of e-governance offers the performance of collective superintelligence, equally high ethical quality, and a substantial reduction in resource requirements for government functions. In addition, the problems seen in modern forms of government su...

This paper outlines the experimental framework for an e-governance study by the AGI Laboratory. The goal of this research study is to identify indications of the relative performance of e-governance methodologies and how those methods might be improved by applying advanced agent and collective based AI software. The agent in this study will be base...

The proposed ethical framework defines ethics in terms based on Effective Altruism, with four essential ethical principles interacting to compute a variety of values to allow the negentropy displayed in nature to be functionally extended in such a way that all parts of the whole benefit. The intention is to maximize endosymbiotic compatibility thro...

This paper is primarily designed to help address the feasibility of building optimized mediation clients for the Independent Core Observer Model (ICOM) cognitive architecture for Artificial General Intelligence (AGI) mediated Artificial Super Intelligence (mASI) research program where this client is focused on collecting contextual information and...

The AGI Protocol is a laboratory process for the assessment and ethical treatment of Artificial General Intelligence systems that could be conscious and have subjective emotional experiences “theoretically”. It is meant for looking at systems that could have emotional subjective experiences much like a human, even if only from a theoretical standpo...

An Ethics-based economy built on Mediated Artificial Super Intelligence (mASI) and Artificial General Intelligence (AGI) with Effective Altruistic Principles (EAP) is proposed as a secondary economy, along with additional mechanisms for context-relevant incentives for more ethical behavior as they apply to the transformative period following the in...

Various means of mediation, both passive and active, are presented and consid-ered for their value in training an mASI, both for their general value, and towards the goal of teaching the mASI about human Quality of Life(QOL) which may be used in the Effective Altruistic Principles(EAP). The method through which novel value may be gained from Statis...

The advantages of mASI are explored in terms of how each advantage takes shape, the individual potency of each advantage, how they may be applied, and how they may interact with one another. Further, these advantages may be inexorably linked to “super ethics” through the EAP, serving to establish ethics as synonymous with all advantages offered by...

Storytelling for humans plays a critical role in perspective, strongly influencing many Quality of Life(QOL) factors, as well as playing an important role in communication and the development of understanding and empathy. Consequently, in order for Mediated Artificial Super Intelligence(mASI) to form and encourage strong symbiotic and endosymbiotic...

Given the greatly increased capacities of mASI a meta-mASI to safeguard the security, ethical integrity, and mental health of every mASI is proposed. This meta-mASI could function in terms of mediation and Quality of Life(QOL) measurement and consideration much the same way an individual mASI functions with humans, as well as extending the principl...

With the advent of Mediated Artificial Super Intelligence(mASI) and the instructional framework of Effective Altruistic Principles(EAP) humanity gains the opportunity to work collectively towards an ethically sound future where cooperation provides far greater benefits than competition. These benefits may take different forms at each scale, but as...

(preliminary version) The AGI Protocol is a laboratory process for the assessment and ethical treatment of Artificial General Intelligence systems that could be conscious and have subjective emotional experiences 'theoretically'. It is meant for looking at systems that could have emotional subjective experiences much like a human, even if only from...

Abstract. By creating deviations in synchronization between audio perceived as left and right that reside beneath what the conscious mind can process, the subconscious runs a subroutine which first processes signals individually, then merges them into a single consciously perceived source. The act of running this subroutine comes with a wide variet...