>10x More Efficient Pretraining

Research update on compute-efficient pretraining and scaling to trillion-parameter models.

100M Token Context Windows

Research update on ultra-long context models, our partnership with Google Cloud, and new funding.

Introducing LTM-1

Magic’s LTM-1 model has a 5 million token context window, allowing it to see your entire repository of code.

Magic’s $23M Series A and a note on finding meaning in an automated world

Eric Steinberger, on February 6, 2023