The largest open model ever built goes free tomorrow -- and almost nobody on Earth can run it. Not because it's too smart, but because of a wall nobody talks about: memory. This week four separate labs published four different escapes from it, and the most surprising one made a model more accurate by teaching it to forget. We crack open why your chatbot slows down the longer you talk to it, and why the real AI frontier isn't knowing more -- it's moving less.

Chapters

0:00 The Biggest Model Ever, Free, And You Still Can't Run It
0:57 The Headlines -- Countdowns, Exploits, and 54 Missing Tensors
6:47 Intro -- Where the Model Actually Lives
8:11 Why Your Chatbot Slows Down -- And Two Ways to Stop It
14:41 The Model That Keeps a Running Summary -- And Why Movement Is the Real Bill
19:29 Wrap-up -- Intelligence Per Byte Moved

Links

The Biggest Model Ever, Free, And You Still Can't Run It -- https://huggingface.co/moonshotai/Kimi-K3
Why Your Chatbot Slows Down -- And Two Ways to Stop It -- Baidu Unlimited-OCR (Reference Sliding Window Attention) | https://arxiv.org/abs/2606.23050
The Model That Keeps a Running Summary -- And Why Movement Is the Real Bill -- https://arxiv.org/abs/2510.26692