Contact us

Aleph Alpha
Blog

Research, engineering and perspectives from the Aleph Alpha team.

In awe at the scale of these tensors – a gentle introduction to Unit-Scaled Maximal Update Parametrization

Research 29/10/2024
Words don’t come easy (… to LLMs): Universal Text-Encoding for dynamic, multi-lingual alphabets revolutionizing efficiency and effectiveness for LLM training and inference

Research 29/08/2024
Open-sourcing Codebase Scaling for Non-commercial Research

Research 26/08/2024
Introducing Pharia-1-LLM: transparent and compliant

Research 26/08/2024
Quality Diversity through AI Feedback

Research 01/06/2023
Luminous Performance Benchmarks

Research 20/02/2023
Aleph Alpha and Graphcore demonstrate 80% sparsified AI Model

Research 17/10/2022
Luminous-Explore – A model for world-class semantic representation

Research 23/09/2022
Alignment and emotions for humans and AI: If we want to trust AI, we may need to hurt it

Other 23/08/2022