• AI, But Simple
  • Posts
  • Recursive Self-Improvement, Ternary 27B Model for Laptops, Jev Architecture

Recursive Self-Improvement, Ternary 27B Model for Laptops, Jev Architecture

AI, But Simple Issue #120

Recursive Self-Improvement, Ternary 27B Model for Laptops, Jev Architecture

AI, But Simple Issue #120

For this week’s research update, the community was fixated on Typesafe’s system-1 thinking model (Jev) [blog], recursive self-improvement, and a 27B ternary quantized model that fits on a 16GB laptop GPU [model].

We'll explain these developments and how they work visually, analyze some results, and watch key movements to keep you updated in no time.

Subscribe to keep reading

This content is free, but you must be subscribed to AI, But Simple to continue reading.

Already a subscriber?Sign in.Not now