1000 Designs a Day: Neural Concept's Thomas von Tschammer on AI-Native Engineering
TL;DR
Neural Concept is replacing days-long physics simulations with AI models that deliver results in minutes, enabling automotive manufacturers to explore thousands of designs daily rather than dozens annually. This shift allows engineers to focus on high-level trade-offs while agentic co-pilots handle iterative optimization across domains like aerodynamics, crash safety, and thermal management.
⚡ The Speed Revolution in Engineering 3 insights
Simulation time compressed from days to minutes
Traditional physics-based solvers require days to run complex crash or aerodynamics simulations, creating severe bottlenecks in design iteration loops.
Thousand-fold increase in design exploration
Neural Concept enables clients like Jaguar Land Rover to evaluate over 1,000 aerodynamic designs per day, compared to previous limits of roughly 50-100 designs annually.
Three eras of engineering evolution
The industry has progressed from physical prototyping and hand-drafting to computer-aided design with physics simulations, and now to AI-native prediction models that augment traditional methods.
🎯 Domain-Specific AI Models 3 insights
Specialist models for distinct physics domains
Neural Concept builds separate models for aerodynamics, crash safety, thermal management, electromagnetism, and structural dynamics, each capturing the intuitive physics of complex vehicle systems.
Hybrid training on simulation and real-world data
Models are trained on both numerical simulation outputs and physical test data from wind tunnels or crash labs, capturing phenomena that pure simulation often misses.
Customer-specific fine-tuning preserves know-how
Rather than using general foundation models, the company fine-tunes models on each manufacturer's proprietary data to capture specific design practices and institutional knowledge.
🤖 Agentic Workflows and Strategic Applications 3 insights
Engineering co-pilots integrate with CAD platforms
The system functions as an agentic co-pilot that calls domain-specific prediction models as tools and autonomously executes design changes within core CAD platforms.
Formula 1 circumvents strict compute restrictions
Formula 1 teams use Neural Concept specifically because racing regulations limit the computational resources allowed for aerodynamic optimization between races.
AI generates surprising move-37 design solutions
The technology occasionally produces non-intuitive designs that alert human engineers to new possibilities in the optimization space they might not have considered.
Bottom Line
Engineering teams should adopt AI-native simulation tools to compress design iteration cycles from days to minutes, enabling exponential exploration of design space while reserving expensive physical prototyping and high-fidelity simulation for final validation stages.
More from Cognitive Revolution
View all
AI:AM #4: Cameron on Model Consciousness, Duvenaud's Gradual Disempowerment, swyx's AI-Eng Alpha
Consciousness researcher Cameron Berg demonstrates that frontier AI models score 30-45% on scientific consciousness indicators using automated theory-based evaluation, while revealing that internal "valence" representations governing welfare states can be directly steered to impact model safety and alignment behaviors.
Compute Improves Compute + Europe 2031
The hosts analyze a fragile moment in AI markets where leveraged speculation in Korean semiconductor stocks, Nvidia's aggressive buyback strategy, and regulatory delays of next-generation models reveal a financial ecosystem racing toward a potential 2028 AGI inflection point that
The God We Deserve: Nonzero's Robert Wright on AI as Humanity's Ultimate Test
Robert Wright argues that modern AI reverses the 1956 assumption that understanding the mind must precede building intelligence, instead reverse-engineering cognition through evolutionary-like training processes that we cannot fully control, leaving humanity's survival dependent on achieving species-scale cooperation and moral enlightenment.
Swyx on AI.Engineer + State of SWE
The hosts reflect on the need for cognitive empathy toward the Trump administration's AI safety interventions while analyzing Dean Ball's move to OpenAI to navigate frontier policy challenges, as the industry faces potential secret deployments of recursively self-improving models.