Singularity Notes

Re-examining mid-training as the strategic centerpiece of the LLM pipeline — how it builds the knowledge foundation for agentic RL, and how RL signals are now flowing backward to improve mid-training itself

A Step-by-Step Walkthrough using Slime and SWE-Bench as an Example

From GPU Memory Budgets to Framework Architectures

Low-Resource RLVR for Transforming Instruct Models into Reasoning Models

Efficient Architectures for Agentic Tasks

Is Reality an Interface?

AGI at the Crossroads

LLMs, Time, and Human-Like Cognition