#124 Foundation PRO edition
Archive 124 issues
#123 Architecture PRO edition
Looped Transformers, Simply Explained
#122 Inference
Context Self-Management, Generation for Understanding, Disaggregated Quantization
#121 Agents
Claude Opus 5.5, Agent Swarms Writing Proofs, Cheap Sparse Models
#120 Architecture
Recursive Self-Improvement, Ternary 27B Model for Laptops, Jev Architecture
#119 LLMs PRO edition
Random Attention, Flow Matching for VLAs, Tencent's Speech Foundation Model
#118 Agents PRO edition
RL Training Inside Harnesses, Stolen Reasoning Traces, Judging Agents
#117 Architecture PRO edition
How DeepSeek’s Architecture Actually Works
#116 Training PRO edition
Persistent AI memory, AI watermarking, on-policy distillation
#115 Architecture PRO edition
BDH-CQ: A 150M model just broke the ARC-AGI cost curve
#114 LLMs PRO edition
A Simple Guide to LLM Activation Steering With Control Systems
#113 Papers PRO edition
The Best ICML Papers of 2026, Simply Explained
#112 Interp. PRO edition
Sparse Autoencoders (SAEs), Simply Explained
#111 LLMs PRO edition
Foundation Models, Simply Explained
#110 RL PRO edition
Multi-Agent RL, Simply Explained
#109 LLMs PRO edition
Diffusion Language Models (DLMs), Simply Explained
#108 Agents PRO edition
The Math-Based Guide to RAG, MCP, and Agents
#107 Architecture PRO edition
Joint-Embedding Predictive Architecture (JEPA), Simply Explained
#106 Training PRO edition
On-Policy Distillation for LLMs, Simply Explained
#105 Architecture PRO edition
The Dragon Hatchling (BDH), Simply Explained
#104 LLMs PRO edition
Multi-Token Prediction, Simply Explained
#103 Theory PRO edition
Deep Evidential Regression, Simply Explained
#102 Agents PRO edition
Self-Improving Agents, Simply Explained
#101 Safety PRO edition
Reward Hacking, Simply Explained
#100 Theory PRO edition
Kalman State Space Models, Simply Explained