

530 episodes
by Enoch H. Kang · English
Cut through the noise. We curate and break down the most important AI papers so you don’t have to.

Chain-of-Agents (COA) proposes end-to-end “agent foundation models” (AFMs) that simulate multi-agent collaboration inside one model, avoiding slow multi-agent back-and-forth while retaining planning,…
30 Aug 2025 · 20m · 13 chapters
Compute-optimal scaling for value-based deep reinforcement learning, focusing on how to allocate limited compute between model size, batch size, and update-to-data (UTD) ratio to improve data…
25 Aug 2025 · 16m · 12 chapters
How LLM-based conversational recommendation agents can learn user preferences from dialogue history, reflect on past interactions, and improve diversity via multi-agent debate.
23 Aug 2025 · 17m · 9 chapters
The episode explains why common LLM benchmarks often fail to predict performance at production scale, and introduces a “signal and noise” framework to quantify benchmark reliability.
23 Aug 2025 · 12m · 4 chapters
Recommender systems can create harmful feedback loops because their recommendations shape the user data used for training, biasing future recommendations and potentially causing homogenization (“rich…
21 Aug 2025 · 13m · 6 chapters
Argues “RAG is dead” as a misleading label; retrieval still matters, but teams should replace demo-driven “alchemy” with “context engineering” to reliably assemble the right information for LLMs.
20 Aug 2025 · 20m · 9 chapters
The episode surveys how AI personalization is added to Retrieval-Augmented Generation (RAG) and how that evolves into personalized agent systems, using the academic paper “Survey of Personalization:…
20 Aug 2025 · 25m · 11 chapters
Treatment effect estimation (TE)—estimating causal impact of a “treatment” X on an outcome Y—especially from observational data where correlation ≠ causation.
19 Aug 2025 · 22m · 10 chapters
A Google/Cornell research paper on “text-to-text regression” using regression language models (RLMs) to predict performance of large, complex systems (e.g., Google’s Borg compute scheduler) by…
16 Aug 2025 · 19m · 12 chapters
The episode explains “length explosion” in LLMs—why models trained with reward signals can become overly verbose—and how the ARCS paper “Sample More to Think Less: Group Filtered Policy Optimization…
15 Aug 2025 · 28m · 8 chapters
Meta AI’s DINOv3, a self-supervised vision model (“universal visual encoder”) trained without human pixel labels, emphasizing improved dense/patch-level features for tasks like segmentation, depth,…
15 Aug 2025 · 20m · 9 chapters
Agent Lightning (Microsoft Research) trains multi-step AI agents with reinforcement learning so they improve reliably in messy real-world tasks, without rewriting existing agent code.
14 Aug 2025 · 20m · 12 chapters
The episode explains “error amplification” in next-token prediction (autoregressive language models) and imitation learning, focusing on a 2025 PMLR paper, Computational-Statistical Tradeoffs at the…
14 Aug 2025 · 12m · 5 chapters
The episode explains how AI optimization is shifting from tuning single LLM “model weights” (e.g., RLHF with KL-regularized objectives) to optimizing modular LLM agents (workflow programs with…
12 Aug 2025 · 17m · 11 chapters
Whether chain-of-thought (CoT) prompting in large language models reflects genuine reasoning or a “brittle mirage” caused by training-data pattern matching; includes a “data distribution lens” and…
12 Aug 2025 · 19m · 14 chapters
The “agentic web” paradigm shift where AI agents autonomously perceive, plan, and execute goal-driven tasks across the internet, replacing manual clicking/searching.
11 Aug 2025 · 22m · 8 chapters
The episode argues that today’s LLM “intelligence” is mainly next-token prediction plus assimilation into fixed or prompted schemata, not true accommodation (restructuring schemas when they fail).
10 Aug 2025 · 23m · 10 chapters
The episode argues that AI reasoning can be separated from brute-force scaling via a “reasoning core” and that an LLM can function as an operating system (LLMOS) that orchestrates external tools.
6 Aug 2025 · 19m · 12 chapters
Statistical rigor for mechanistic interpretability (MI) in AI—how to reverse-engineer neural networks by finding features and circuits, while avoiding statistical pitfalls from dependent “cheap” data…
6 Aug 2025 · 18m · 11 chapters
Full-stack alignment argues that aligning AI only to its operator’s local objective (e.g., profit or engagement) can still harm society; it proposes “thick models of value” (TMV) to preserve and…
4 Aug 2025 · 22m · 10 chapters
The Nature (July 2, 2025) paper “A Foundation Model to Predict and Capture Human Cognition” introduces Centaur, a foundation model fine-tuned on human behavioral data to predict and simulate human…
4 Aug 2025 · 19m · 7 chapters
Generative recommendation using Semantic IDs (SIDs), focusing on Snap Inc.’s open-source GRD framework.
4 Aug 2025 · 17m · 8 chapters
The episode explains a new “Hierarchical Reasoning Model” (HRM) for multi-step AI reasoning, arguing that flat LLM-style chain-of-thought can be brittle and computationally shallow, while…
4 Aug 2025 · 12m · 5 chapters
Goal Conditioned Test Time Training (GCTTT) for offline reinforcement learning—dynamically fine-tuning a goal-conditioned policy during evaluation using only relevant, high-value past experience,…
4 Aug 2025 · 14m · 5 chapters