Stories by sonabinu

Expected Attention: KV Cache Compression by Estimating Attention

Delta-Code: How Does RL Unlock and Transfer New Programming Algorithms in LLMs?

One AI Model Creates a Physical Intuition of Its Environment

How to live to 117? Researchers find clues in the oldest woman

No more scribbling: Indian court tells doctors to fix their handwriting

Understanding RL for model training, and future directions with GRAPE

To Understand AI, Watch How It Evolves

The surprisingly lucrative business of making a list of 500 stocks

RL in Name Only?

9/16/25, celebrate a date of mathematical beauty

Why Language Models Hallucinate

Gordon Bowker, Who Came Up with the Idea for the First Starbucks, Dies at 82

The Landscape of Agentic Reinforcement Learning for LLMs

The Theoretical Limitations of Embedding-Based Retrieval

Backpropogation through time: What it does and how to do it (1990) [pdf]

Deep Learning Tuning Playbook

1 2 3 4 5 6 7 8 9 10