Dustin Juliano (@DustinJuliano) header
Dustin Juliano (@DustinJuliano) profile picture

Author of "AI Security" (2016), "AGI Strategy" (TBD) | Student & Researcher in Computer Science | Formal AI | Programming Languages | Applied Type Theory

United States
Joined October 2022
Photo by Dustin Juliano (@DustinJuliano)Photo by Dustin Juliano (@DustinJuliano)Photo by Dustin Juliano (@DustinJuliano)
My primary goal is to initiate the field of formal artificial intelligence and accelerate its adoption through outreach, education, and applied research. Briefly, Formal AI seeks to represent AI systems entirely with human-readable source code and data. This would potentially allow exploiting correspondences in constructive mathematics, intuitionistic logic, type theory, formal methods, formal languages and grammars, program verification, and many others. There are two broad objectives in Formal AI. The first objective is to comprehensively show, end-to-end, that an AI system provably adheres to its specification and is free of unintended behaviors. The second objective is to constrain the set of solutions to only those that are human-readable, in both source code and data form. All benefits, such as efficiency, modularity, transparency, trustworthiness, governance, interpretability, control, alignment, safety, and security are derived from these two objectives. Formal AI has numerous open research problems that cannot be solved by one person; a community is needed that spans government, industry, and academia. I believe that there is an urgency to solving Formal AI, for it may potentially address both present and future challenges as we continue to integrate with AI on a global scale. My current focus is to bring more researchers towards this cause while working on specific technical challenges related to programming languages and type theory that can benefit the mission.
2
1,288
Dustin Juliano retweeted
Attackers have frontier AI. Defenders need a frontier AI ecosystem—the best open and closed models, force-multiplied by a global community. During the Hugging Face incident, closed AI blocked essential forensics. An open-weight frontier model helped contain the intrusion. That’s why we created the Open Secure AI Alliance.
AI security advances when the industry builds in the open, together. We're introducing the Open Secure AI Alliance with industry leaders to develop new techniques and tools to safeguard software and agents. By sharing models, tooling and research in the open, we can broaden the community of defenders. Learn more about the founding members’ contributions: nvda.ws/4pD8Fc5
2,076
4,140
909
36,336
11,589,892
One of the most important positions I hold on AI, as contrarian as it may be, is that we are vastly overestimating the resources required to train and operate AI in the future, especially AGI.
12
2
4
22
2,600
Concepts of Formal AI, Ep. 1: “AI = Program”. This episode uses Artifact 1 to prove the correspondence between AI models and computer programs. This is a foundational concept for understanding Formal AI R&D.
1
1
2
204
This is the link to the code for Artifact 1 used in today's episode. It is fully reproducible and includes a pre-trained model. It has instructions to reconstruct the training data, train the model, and perform evaluations to demonstrate the principle. github.com/dustinjuliano/cfa…
119
Artifact 1 has been updated with better documentation and a new URL. This project is intended to be used to illustrate the point that ML models are, in some sense, (obfuscated) computer programs, in the upcoming "Concepts of Formal AI" (CFAI) series. github.com/dustinjuliano/cfa…
1
130