Causal Reasoning in Autoregressive Language Models: A Mechanistic Interpretability Approach
K. Zhang, M. Hoffmann, L. Chen, A. Petrov · 2025
AI Research Company
build intelligence systems that reason, create, and collaborate.
Our work sits at the intersection of fundamental research and practical engineering. We don't build for hype — we build for permanence. Every system we ship is designed to outlast the cycle.
Systems that chain thoughts together, verify their own logic, and arrive at conclusions without human prompting. Not instruction-following — genuine reasoning.
Understanding across text, audio, code, and visual domains simultaneously. Our models don't just process — they perceive. Context is everything.
Software that writes software. Systems that design systems. We treat code generation not as a feature, but as an engineering discipline with its own principles.
K. Zhang, M. Hoffmann, L. Chen, A. Petrov · 2025
S. Yamamoto, R. Ortíz, F. Weber · 2025
A. Petrov, J. Müller, T. Adeyemi · 2024
L. Chen, M. Hoffmann, K. Zhang · 2024
Research Scientists. Engineers. Philosophers.
We don't care about your degree. We care about your questions. If you think in systems and build with rigor, we want to hear from you.