This is insane, here’s how this works:

Normal LLMs (like Grok or GPT variants) store their "kn0wledge" in billions of numbers (weights)

Each weight is usually a high-precision decimal (like 3.14159), stored using 16 bits per weight. This makes the model huge in memory and… https://t.co/P2W0pNNqxq

— AI Breakfast (@AiBreakfast) 5 janvier 2026

This is insane, here’s how this works: Normal LLMs (like Grok or GPT variants) store their "kn0wledge" in billions of numbers (weights) Each weight is usually a high-precision decimal (like 3.14159), stored using 16 bits per weight. This makes the model huge in memory and

→ View original post on X — @aibreakfast