We build across the stack: foundation models, inference, voice, agentic architectures, robotic systems and reinforcement learning.
If a problem is interesting and tractable, we work on it.
Through systems of records, engagements, predictions, states and agents.
Trading unique parameters for recurrent depth, and attempting to make single-user decode compute-bound by keeping a looped transformer block resident in L2 cache.
An independent mechanistic and adversarial audit of Sarvam-30B and Sarvam-105B across 14 Indian languages. The models are 6x more likely to comply with harmful requests in Indian languages than in English.
Overhear DEFUNCT A voice-native operating system. Email, web search, tasks and workflows through conversation. No screen required.
Mail us at hi@goedelmachines.com