azetta ai
Physics Grounded AI Research Lab.
// OUR MISSION
AI Should Be Safe, Transparent, and Sustainable.
"People outside the field are often surprised to learn that we do not understand how our own AI creations work. This lack of understanding is unprecedented in the history of technology."
— Dario Amodei, CEO Anthropic · 2025
▶ The Black Box Problem
Today's AI is a black box running on brute force. Models grow larger every year, yet no one can explain why they hallucinate, discriminate, or fail. Bias lives inside the weights, beyond our reach, and the Frontier Labs' attempts at reverse-engineering AI are extremely inefficient — Anthropic itself admits that fully understanding a model with their approach would take far more compute than was needed to train it in the first place.
We believe this is because frontier models are fundamentally opaque, and that a viable, scalable solution has to go back to the foundations. Our mission is to rebuild AI so that every decision is explainable and every behaviour is correctable — models that improve and scale in smarter, far more efficient ways.
▶ Every Major AI Risk Traces Back to Interpretability
Alignment
click to revealHarmful AI incidents hit 233 in 2024 — +56% YoY (Stanford HAI). We cannot verify what a model is optimising for — goals appear aligned but remain uninspectable.
Hallucinations
click to revealLLMs hallucinate on 75%+ of legal queries. We can detect errors in outputs — without interpretability, we cannot stop them at the source.
Bias & Fairness
click to revealLLMs preferred white-sounding names 85% of the time in hiring simulations. EEOC's first AI bias settlement: $325K. Bias lives inside weights — beyond our reach.
Privacy Leakage
click to revealResearchers extracted PII from ChatGPT for ~$200. 5%+ of outputs are verbatim training copies. No mechanism exists to audit what a model retained.
IP Exposure
click to revealCourts hold companies liable for AI outputs (Air Canada, 2024). Without interpretability, IP exposure is unquantifiable — we cannot trace which training data shaped a model's behaviour.
Harmful Use
click to revealEU AI Act mandates human oversight for high-risk AI — non-compliance: up to 6% of global revenue. Safety filters are surface patches on opaque systems.
▶ Why This Matters
The Ceiling on Progress
Model self-improvement requires interpretability. Without it, we cannot guide models reliably or safely.
Regulated Industries Are Locked Out
Healthcare, finance, legal, and defence cannot deploy black-box AI where decisions must be audited or legally defended.
Full Automation Requires Control
You cannot delegate what you cannot inspect — and today, we cannot inspect these systems.
// OUR APPROACH
Reimagining AI Through a Physics Lens.
We believe information has its own physics. Reimagining AI through this lens reveals a fundamental mathematical structure — and building based on it gives us models that are interpretable, steerable and efficient by design.
- Interpretable
- One neuron, one concept. Full audit trail from input to output.
- Steerable
- Target specific neurons. Correct behaviour directly — no retraining.
- Efficient
- 10× fewer parameters, 90% faster training.
- Performant
- Performance matches or exceeds State of the Art.
// OUR RESEARCH
Pioneering the Field of Physics Grounded AI.
YAT KERNEL
The Yat Kernel is a physics-grounded mercer kernel that captures both alignment and proximity to create highly efficient gravity wells in representation space
ⵟ(x, w) = (x·w)² / ‖x − w‖²
Unlike dot products and cosines, the YAT kernel measures how much a weight vector acts as an attractor for an input. Each neuron bends representation space around itself — creating distinct, non-overlapping gravity wells. The result: monosemantic neurons by design, interpretability without any post-hoc approximation.
SLAY: Spherical Linearized Attention
A geometry-aware, linear-time attention mechanism powered by the YAT kernel — matching softmax attention while outperforming prior linear methods. With K. Choromanski.
Read paper → arXiv · May 2026A Universal RKHS from Polynomial Alignment & IMQ Distance
The mathematical foundation of the YAT kernel: a universal, characteristic kernel with provable positive-definiteness and explicit generalization bounds.
Read paper → arXiv · Jun 2026Bernstein–Schur Kernels
A random-feature construction via sketched modulation and radial randomization — unbiased, low-variance, and computationally efficient.
Read paper →// OUR PRODUCTS
We Build White Box Models + the Tools to Understand them.
As we establish and grow the field of Physics Grounded AI, we also build products that help researchers, engineers and enterprises have access to our research findings seamlessly, safely and ready to scale.
PERIODICA
// The first MLOps platform built for interpretability
Upload any AI model — Periodica maps every neuron to a concept and lets you steer behaviour directly. No retraining. No black boxes.
Drop your model or pick a demo
PyTorch · TensorFlow · ONNX · HuggingFace
← Click a flagged neuron or use Search to probe any concept
Aether Models
// Fully interpretable SOTA models, available via API
Aether models are Physics Grounded AI in production. Fully interpretable and steerable models with State of the Art Performance with ~10X less parameters.
// WHO WE ARE
The Founding Team.
Mathematical rigour, entrepreneurial experience, and product acumen.
Taha Bouhsine
Co-Founder & CEO
AI Google Developer Expert and architect of the Physics Grounded AI framework. Mathematician, computer scientist, and electrical engineer researching interpretable, efficient neural networks, representation learning, and the geometry of how models understand the world. Builds rigorous, explainable AI from first principles.
Jose Miguel L.
Co-Founder & CPO
Ex-Apple Engineering Product Manager for AI/ML products. Founding team at YC-backed startup, leading Product, Data and Tech teams. Schwarzman Scholar and Columbia MBA + MS in AI/ML.
Help us rebuild AI from first principles.
We're building the foundations of transparent, physics-grounded AI — and we're looking for the people who want to build it with us.