Sakana introduces new AI architecture, ‘Continuous Thought Machines’ to make models reason with less guidance — like human brains

Similar to children leaving home and learning to explore the world independently, a newly published research paper illustrated the success story of the independent development of TI, starting from absolute zero, as Kristjan Port reports in R2's technical commentary.

Sakana introduces new AI architecture, ‘Continuous Thought Machines’ to make models reason with less guidance — like human brains

While the CTM shows strong promise, it is still primarily a research architecture and is not yet production-ready out of the box.

How Continuous Thought Machines learn to ‘think’ more like us

Sakana AI's Continuous Thought Machine enhances AI's alignment with human cognition, promising a future of more trustworthy and efficient technology.