Archive 124 issues

2026 41

1. #124 Oct 26 Decision Models, World Action Models, Egocentric Video Foundation PRO edition
2. #123 Oct 19 Looped Transformers, Simply Explained Architecture PRO edition
3. #122 Oct 5 Context Self-Management, Generation for Understanding, Disaggregated Quantization Inference
4. #121 Sep 28 Claude Opus 5.5, Agent Swarms Writing Proofs, Cheap Sparse Models Agents
5. #120 Sep 21 Recursive Self-Improvement, Ternary 27B Model for Laptops, Jev Architecture Architecture
6. #119 Sep 14 Random Attention, Flow Matching for VLAs, Tencent's Speech Foundation Model LLMs PRO edition
7. #118 Sep 7 RL Training Inside Harnesses, Stolen Reasoning Traces, Judging Agents Agents PRO edition
8. #117 Aug 31 How DeepSeek’s Architecture Actually Works Architecture PRO edition
9. #116 Aug 24 Persistent AI memory, AI watermarking, on-policy distillation Training PRO edition
10. #115 Aug 17 BDH-CQ: A 150M model just broke the ARC-AGI cost curve Architecture PRO edition
11. #114 Aug 10 A Simple Guide to LLM Activation Steering With Control Systems LLMs PRO edition
12. #113 Aug 3 The Best ICML Papers of 2026, Simply Explained Papers PRO edition
13. #112 Jul 27 Sparse Autoencoders (SAEs), Simply Explained Interp. PRO edition
14. #111 Jul 20 Foundation Models, Simply Explained LLMs PRO edition
15. #110 Jul 13 Multi-Agent RL, Simply Explained RL PRO edition
16. #109 Jul 6 Diffusion Language Models (DLMs), Simply Explained LLMs PRO edition
17. #108 Jun 29 The Math-Based Guide to RAG, MCP, and Agents Agents PRO edition
18. #107 Jun 22 Joint-Embedding Predictive Architecture (JEPA), Simply Explained Architecture PRO edition
19. #106 Jun 15 On-Policy Distillation for LLMs, Simply Explained Training PRO edition
20. #105 Jun 8 The Dragon Hatchling (BDH), Simply Explained Architecture PRO edition
21. #104 Jun 1 Multi-Token Prediction, Simply Explained LLMs PRO edition
22. #103 May 25 Deep Evidential Regression, Simply Explained Theory PRO edition
23. #102 May 18 Self-Improving Agents, Simply Explained Agents PRO edition
24. #101 May 11 Reward Hacking, Simply Explained Safety PRO edition
25. #100 May 4 Kalman State Space Models, Simply Explained Theory PRO edition
26. #99 Apr 27 Graph Neural Networks (GNNs), Simply Explained Architecture PRO edition
27. #98 Apr 20 World Models, Simply Explained RL PRO edition
28. #97 Apr 13 Reinforcement Learning for Large Language Models, Simply Explained RL PRO edition
29. #96 Apr 6 MicroGPT, Simply Explained LLMs PRO edition
30. #95 Mar 30 Multimodal Large Language Models (MLLMs), Simply Explained Multimodal PRO edition
31. #94 Mar 23 Conformal Prediction: Reliable Uncertainty for Machine Learning Theory PRO edition
32. #93 Mar 16 Vision Language Models (VL-JEPA), Simply Explained Multimodal PRO edition
33. #92 Mar 9 The Lottery Ticket Hypothesis, Simply Explained Theory PRO edition
34. #91 Mar 2 Linear Attention For Transformers (Kimi Linear), Simply Explained Architecture PRO edition
35. #90 Feb 23 NeurIPS 2025 Paper Awards (The Best Papers of 2025) Papers PRO edition
36. #89 Feb 16 The Best NeurIPS Papers of 2025, Simply Explained Papers PRO edition
37. #88 Feb 9 NRGPT: Combining Energy-Based Models With GPT LLMs PRO edition
38. #87 Feb 2 Fine-Tuning for LLMs, Simply Explained Training PRO edition
39. #86 Jan 26 A Deep Dive into Modern Transformers: RoPE, Activation Functions, Quantization Inference PRO edition
40. #85 Jan 19 A Deep Dive into Modern Transformers: Optimizing Attention Inference PRO edition