GPT-5.6 vs Claude Fable 5 for Physical AI, which performs best?: In this study, we tested four frontier AI models on five complex physical modeling and simulation challenges using the Dyad AI harness. While Claude Fable 5 delivered the highest overall accuracy, GPT-5.6 Sol emerged as the strongest value option, and the findings reveal that the AI harness itself has an even greater impact on engineering outcomes than the choice of model. Read more.
Meet JuliaHub at JuliaCon 2026: We're heading to JuliaCon 2026 from August 10–15 in Mainz, Germany! Don't miss presentations from the JuliaHub team, including the highly anticipated State of Julia session showcasing the newest advancements across the Julia language and ecosystem. See the JuliaHub lineup of speakers at JuliaCon here.
With Dyad 3.3 Multibody Goes 3D: The headliner feature is genuine 3D multibody mechanics, introducing native joint sets, tire models, URDF import, and 3D rendering. Beyond mechanical simulation, this release dramatically reduces editor friction with compiler-driven LSP syntax highlighting, streamlined enum parameter typing, and an upgraded AI agent that dynamically tracks installed package versions in real time. Read the blog post.
Agentic Engineering Design Tools: This white paper looks at how engineering organizations can move beyond AI copilots to autonomous engineering workflows by adopting the right agentic engineering tools. It explores why engineering organizations are increasingly facing a productivity gap with rising complexity, the difference between a copilot and an autonomous engineering agent, how physics-guided AI leads to production-ready workflows and the business case for agentic engineering, including faster development and improved efficiency. Download it here.
Tradespace Exploration with the Dyad Agent: Discover how the Dyad Agent simplifies engineering optimization by using natural language to modify models, run parameter sweeps, and evaluate tradeoffs—all without manual scripting. Using a real-world wastewater treatment example, the blog shows how AI-driven simulation helps engineers make faster, better-informed design decisions. Read it more.
Building a Validated HL-20 Model with the Dyad Agent: Translating complex engineering specs into simulation models has traditionally been a slow, manual, and error-prone process. In a new technical deep dive, JuliaHub demonstrates how the Dyad Agent automated the construction of a simulation model for NASA’s complex HL-20 hypersonic re-entry vehicle by directly reasoning over source Markdown, atmospheric databases, and DAVE-ML aerodynamic tables. Utilizing continuous compiler-in-the-loop checks alongside reference validation against historical NASA flight data, the agent ensures the resulting system is both structurally and physically accurate, marking a major step forward for physical AI in engineering workflows.
ChromOps.jl: High-Order Simulation and Discrete Forward Sensitivity Analysis for Chromatography Models: ChromOps.jl introduces a fully differentiable Julia solver for mechanistic chromatography models, combining high-order spatial discretization with discrete forward sensitivity analysis to make gradient-based parameter estimation and optimization more efficient. The study demonstrates accurate gradients without hand-derived derivatives, enabling faster and more accessible simulation-driven optimization for chromatography applications. Find out more.
JuliaHub at American Modelica & FMI Conference 2026: JuliaHub is a Platinum Sponsor of the American Modelica and FMI Conference taking place at the Georgia Institute of Technology in the Aerospace Systems Design Laboratory from October 12–14, 2026. It is organized by NAMUG, the North American Modelica Users Group, in cooperation with the Modelica Association(NAMUG). Bringing together engineers, researchers, and industry leaders, NAMUG is a key forum for advancing modeling, simulation, and digital engineering. Join the JuliaHub team to discover how our Modelica-powered solutions are helping organizations build faster, more accurate simulations and accelerate innovation.
JuliaHub at ACoP 2026: JuliaHub will be at the 2026 American Conference on Pharmacometrics (ACoP 2026), taking place October 11–14, 2026, at the Gaylord National Resort & Convention Center in National Harbor (Oxon Hill), Maryland, USA. As one of the leading global events in pharmacometrics, ACoP brings together researchers, scientists, and industry leaders to advance quantitative approaches in drug development. If you're attending, be sure to connect with the JuliaHub team to learn how Julia and Pumas are accelerating modeling, simulation, and pharmacometric innovation.
Recent JuliaHub Webinars: JuliaHub provides free one-hour Webinars on topics of interest to Julia users. Nearly 100 past Webinars are available online. Click here to watch.
This Month in Julia World: This Month in Julia World is a newsletter from Stefan Krastanov with up-to-date information about Julia events, new releases and more. Read it here.
Nouvelles Julia - Julia News en Français: Nouvelles Julia is a newsletter in French with the latest Julia news. Read it here.
New Blog Posts from SciML: SciML has published new blog posts. You can read them here.
Julia Dispatch Podcast: Julia Dispatch is a Julia podcast from Dr. Chris Rackauckas (JuliaHub VP of Modeling and Simulation) and Dr. Michael Tiemann. Watch it here.
JuliaHub Digital Twin Solutions and Consulting: We help enterprises build deployable and scalable solutions leveraging SciML to create highly accurate and trustworthy Digital Twins. Applications span asset health monitoring, optimization and predictive maintenance, process optimization, model-based control, design optimization, and internal or external simulation tools. We also offer consulting and technical support. Schedule a consultation with our solutions team to discuss your use case.
Careers at JuliaHub: JuliaHub is a fast-growing tech company with fully remote employees in 20 countries on 6 continents. Click here to learn more about exciting careers and internships with JuliaHub.
Julia Expertise Needed at University of Glasgow: Dr. Eric Silverman, Research Fellow at the University of Glasgow, seeks a Research Associate for a 5-year research project on computational modeling for public health using an agent-based modeling framework developed in Julia. Julia experience and a PhD are required for this position. Click here for more information and to apply.
Julia and JuliaHub in the News
Julia Blog Posts
GPT-5.6 vs Claude Fable 5 for Physical AI, which performs best?
This Month in Julia World (Stefan Krastanov)
Nouvelles Julia (Pierre Navaro)
Julia: Working with Vectors and Matrices (Angles and Linearity) — Part 3 (Ângelo Galvão)
Julia: Working with Vectors and Matrices — Part 4 (Ângelo Galvão)
Julia’s Hidden Superpower Nobody Talks About (Emma Boudreau)
How the Dyad Agent Builds a Validated HL-20 Model (David Dinh)
JuliaHub at JuliaCon 2026 (Jasmine Chokshi)
10 Random Julia Tips To Help You On Your Way (Emma Boudreau)
Tradespace Exploration with the Dyad Agent (David Dinh)
Anatomy of a Hybrid AI Agent: Combining Prolog, Julia and Lisp (Gabriel Schipor)
Why Prolog, Lisp and Julia Struggle to "Talk" to Each Other (Gabriel Schipor)
Upcoming Julia and JuliaHub Events
Johannes Gutenberg University Mainz (Germany, near Frankfurt): JuliaCon 2026 with JuliHub, August 10-15
Oxon Hill, Maryland, USA: American Conference on Pharmacometrics (ACoP 2026), October 11-14
Atlanta, USA: American Modelica & FMI Conference 2026, October 12-14
Contact Us: Please contact us if you want to:
Obtain pricing for Dyad and Julia consulting projects for your organization
Schedule Dyad or Julia training
Share information about exciting new Julia case studies or use cases
Partner with JuliaHub to organize a Julia event online or offline
About JuliaHub, Julia and Dyad
Dyad combines physics-based modeling with scientific machine learning(SciML) for mission-critical engineering. Dyad is fully agentic in its design, making it possible for engineers to carry out complex workflows through natural language interaction. Dyad integrates code, diagrams and agentic workflows in a seamless tool driving 10x productivity. Leveraging the Julia and the SciML ecosystem under the hood, Dyad also benefits from significantly higher performance compared to the competition, often being 100x faster at simulating complex physics. Teams leverage Dyad to build smarter, faster, and more reliable systems without compromising the rigor of traditional engineering, supporting use cases from predictive maintenance to real-time performance tuning and over-the-air updates. The Dyad tool powered by Julia and SciML is free to use. Get started here.
JuliaHub is a fast and easy-to-use code-to-cloud platform that accelerates the development and deployment of Julia programs. JuliaHub users include some of the most innovative companies in a range of industries including pharmaceuticals, automotive, energy, manufacturing, and semiconductor design and manufacture.
Julia is a high performance open source programming language that powers computationally demanding applications in modeling and simulation, drug development, design of multi-physical systems, electronic design automation, big data analytics, scientific machine learning and artificial intelligence. Julia solves the two language problem by combining the ease of use of Python and R with the speed of C++. Julia provides parallel computing capabilities out of the box and unlimited scalability with minimal effort. Julia has been downloaded by users at more than 10,000 companies and is used at more than 1,500 universities. Julia co-creators are the winners of the prestigious James H. Wilkinson Prize for Numerical Software and the Sidney Fernbach Award.
