Best AI papers explained

Enoch H. Kang

Cut through the noise. We curate and break down the most important AI papers so you don’t have to.

Episodes · 25

When to Trust the Cheap Check: Weak and Strong Verification for Reasoning

Oct 3, 2026 · 24m

Theoretical Limits of Language Model Alignment

Oct 1, 2026 · 24m

DT2: Decision-Targeted Digital Twins

Sep 29, 2026 · 12m

Self-Play Pretraining with Zero Data

Sep 27, 2026 · 21m

Language models need sleep: learning to self-modify and consolidate memories

Sep 27, 2026 · 21m

Jev Creator: System One models for Prod, not God

Sep 23, 2026 · 21m

Detecting and countering misuse of AI: September 2026

Sep 22, 2026 · 22m

Position: LLMs can’t jump

Sep 22, 2026 · 20m

Jailbreaking Jailbreaks: A Proactive Defense for LLMs

Sep 20, 2026 · 22m

When Agents Slow Down: Understanding LLM Agents’ Test-Time Strategies via Elo-per-token Analysis

Sep 18, 2026 · 22m

Thinking with Looped Flows

Sep 17, 2026 · 20m

Multi-Turn LLM Conversations under the Least-Recently-Used Policy: Mean-Field Asymptotics

Sep 17, 2026 · 22m

Breaking the Token Ceiling: Distilling Smaller, Stronger Byte Models

Sep 14, 2026 · 23m

Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs

Sep 12, 2026 · 21m

Tail-Likelihood Reinforcement Learning

Sep 11, 2026 · 21m

Next-Latent Prediction Transformers Learn Compact World Models

Sep 7, 2026 · 22m

Language Models Can Control Their Own Attention

Sep 5, 2026 · 20m

AI Finds A Way

Sep 4, 2026 · 26m

Superposition Without Interference? Towards Isolated Interventions via Almost Orthogonal Features in Language Models

Sep 3, 2026 · 23m

TTPO: Test-Time Policy Optimization

Sep 3, 2026 · 23m

Demystifying Reinforcement Learning Post-Training of Language Models

Sep 1, 2026 · 20m

Recursive Experiential–Working Memory Evolution for Long-Horizon Agent Harnesses

Aug 31, 2026 · 20m

TailSFT: Filtered Fine-Tuning Improves Post-Training Performance

Aug 30, 2026 · 22m

SPADE: Self-Play in Adaptive Synthetic Executable Environments

Aug 29, 2026 · 21m

Evaluating Skills, Not Just Agents: Agentic Continuous Evaluation of Skills

Aug 27, 2026 · 27m