Edwin Dong

Edwin Dong

RL Training Inside Harnesses, Stolen Reasoning Traces, Judging Agents

RL Training Inside Harnesses, Stolen Reasoning Traces, Judging Agents

AI, But Simple Issue #118

Edwin Dong
Edwin Dong
How DeepSeek’s Architecture Actually Works

How DeepSeek’s Architecture Actually Works

AI, But Simple Issue #117

Edwin Dong
Lalit Julapalli
Edwin Dong, +1
Persistent AI memory, AI watermarking, on-policy distillation

Persistent AI memory, AI watermarking, on-policy distillation

AI, But Simple Issue #116

Edwin Dong
Edwin Dong
ArchitectureArchitecture
BDH-CQ: A 150M model just broke the ARC-AGI cost curve

BDH-CQ: A 150M model just broke the ARC-AGI cost curve

AI, But Simple Issue #115

Edwin Dong
Edwin Dong
LLMsLLMs
A Simple Guide to LLM Activation Steering With Control Systems

A Simple Guide to LLM Activation Steering With Control Systems

AI, But Simple Issue #114

Anurag Shinde
Edwin Dong
Anurag Shinde, +1
PapersPapers
The Best ICML Papers of 2026, Simply Explained

The Best ICML Papers of 2026, Simply Explained

AI, But Simple Issue #113

Edwin Dong
Edwin Dong
(PRO) Sparse Autoencoders (SAEs), Simply Explained
Premium

(PRO) Sparse Autoencoders (SAEs), Simply Explained

AI, But Simple Issue #112

Edwin Dong
Lalit Julapalli
Edwin Dong, +1
Sparse Autoencoders (SAEs), Simply Explained

Sparse Autoencoders (SAEs), Simply Explained

AI, But Simple Issue #112

Edwin Dong
Lalit Julapalli
Edwin Dong, +1
Foundation Models, Simply Explained

Foundation Models, Simply Explained

AI, But Simple Issue #111

Edwin Dong
Edwin Dong
(PRO) Foundation Models, Simply Explained
Premium

(PRO) Foundation Models, Simply Explained

AI, But Simple Issue #111

Edwin Dong
Edwin Dong