All Episodes

CUGA Agent: From Benchmarks to Business Impact of IBM's Generalist Agent

TUMIX: Multi-Agent Test-Time Scaling with Tool-Use Mixture

Meta AI Researcher Explains ARE and Gaia2: Scaling Up Agent Environments and Evaluations

Georgia Tech's Santosh Vempala Explains Why Language Models Hallucinate, His Research With OpenAI

Atropos Health’s Arjun Mukerji, PhD, Explains RWESummary: A Framework and Test for Choosing LLMs to Summarize Real-World Evidence (RWE) Studies

Stan Miasnikov, Distinguished Engineer, AI/ML Architecture, Consumer Experience at Verizon Walks Us Through His New Paper

Small Language Models are the Future of Agentic AI

Watermarking for LLMs and Image Models

Self-Adapting Language Models: Paper Authors Discuss Implications

The Illusion of Thinking: What the Apple AI Paper Says About LLM Reasoning

Accurate KV Cache Quantization with Outlier Tokens Tracing

Scalable Chain of Thoughts via Elastic Reasoning

Sleep-time Compute: Beyond Inference Scaling at Test-time

LibreEval: The Largest Open Source Benchmark for RAG Hallucination Detection

AI Benchmark Deep Dive: Gemini 2.5 and Humanity's Last Exam

Model Context Protocol (MCP)

AI Roundup: DeepSeek’s Big Moves, Claude 3.7, and the Latest Breakthroughs

How DeepSeek is Pushing the Boundaries of AI Development

Multiagent Finetuning: A Conversation with Researcher Yilun Du

Training Large Language Models to Reason in Continuous Latent Space

LLMs as Judges: A Comprehensive Survey on LLM-Based Evaluation Methods

Merge, Ensemble, and Cooperate! A Survey on Collaborative LLM Strategies

Agent-as-a-Judge: Evaluate Agents with Agents

Introduction to OpenAI's Realtime API

Swarm: OpenAI's Experimental Approach to Multi-Agent Systems

KV Cache Explained

The Shrek Sampler: How Entropy-Based Sampling is Revolutionizing LLMs

Google's NotebookLM and the Future of AI-Generated Audio

Exploring OpenAI's o1-preview and o1-mini

Breaking Down Reflection Tuning: Enhancing LLM Performance with Self-Learning

Composable Interventions for Language Models

Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges

Breaking Down Meta's Llama 3 Herd of Models

DSPy Assertions: Computational Constraints for Self-Refining Language Model Pipelines

RAFT: Adapting Language Model to Domain Specific RAG

LLM Interpretability and Sparse Autoencoders: Research from OpenAI and Anthropic

Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models' Alignment

Breaking Down EvalGen: Who Validates the Validators?

Keys To Understanding ReAct: Synergizing Reasoning and Acting in Language Models

Demystifying Chronos: Learning the Language of Time Series

Anthropic Claude 3

Reinforcement Learning in the Era of LLMs

Sora: OpenAI’s Text-to-Video Generation Model

RAG vs Fine-Tuning

Phi-2 Model

HyDE: Precise Zero-Shot Dense Retrieval without Relevance Labels

A Deep Dive Into Generative's Newest Models: Gemini vs Mistral (Mixtral-8x7B)–Part I

How to Prompt LLMs for Text-to-SQL: A Study in Zero-shot, Single-domain, and Cross-domain Settings

The Geometry of Truth: Emergent Linear Structure in LLM Representation of True/False Datasets

Towards Monosemanticity: Decomposing Language Models With Dictionary Learning

RankVicuna: Zero-Shot Listwise Document Reranking with Open-Source Large Language Models

Explaining Grokking Through Circuit Efficiency

Large Content And Behavior Models To Understand, Simulate, And Optimize Content And Behavior

Skeleton of Thought: LLMs Can Do Parallel Decoding

Llama 2: Open Foundation and Fine-Tuned Chat Models

Lost in the Middle: How Language Models Use Long Contexts

Orca: Progressive Learning from Complex Explanation Traces of GPT-4

Toolformer: Training LLMs To Use Tools

Hungry Hungry Hippos - H3

ChatGPT and InstructGPT: Aligning Language Models to Human Intention