Post-training climbed maths, code and tool use on process data written by humans or synthesised under their direction. The research rung has no such corpus. To keep improving, models have to do science — which makes discovery AI's own bottleneck, not an application of it.
This article analyzes why Diffusion LLMs scale less efficiently than Autoregressive (AR) Models, focusing on two core issues: lack of KV caching and intractable sequence likelihood. 👉 Read the full post on Notion: Inherent Limitations of Diffusion LLMs — Notion Page
Welcome to my Blog 👋 This is the very first post on my site. Here I will share thoughts on AI and random thoughts about life. Stay tuned! 欢迎来到我的博客 👋 这是本站的第一篇文章。 我将在这里分享关于 人工智能 的一些研究体会，也会写一些 生活随想。 敬请期待！