Sitemap - 2024 - TheSequence
Edge 450: Can LLM Sabotage Human Evaluations
The Sequence Chat: The End of Data. Or Maybe Not
Edge 449: Getting Into Adversarial Distillation
The Toughest Math Benchmark Ever Built
📽 Webinar: How Convirza Scaled SLMs for Real-Time Call Analytics – Without Breaking the Bank
Edge 448: Meta AI's Technique For Building LLMs that "Think Before they Speak"
Edge 447: Not All Model Distillations are Created Equal
Microsoft's New Framework for Multi-Agent Systems
Edge 446: Can AI Build AI Systems? Inside OpenAI's MLE-Bench
Edge 445: A New Series About Knowledge Distillation
Robotics is Inching Towards it ChatGPT Moment
📽 Fully Virtual: Agents in Production
Edge 444: Learn About Movie Gen: Meta AI's Amazing Audio-Video Generation Model
The Sequence Chat: Thinking About Transformers as Computers
Edge 443: EVERYTHING you Need to Know About State Space Models
Edge 442: If You Thought DeepMind's AlphaFold was Impressive, Wait Until You Learn About AlphaProteo
Edge 441: SSMs Beyond Language
The Sequence Chat: Why Transformers are the Best Thing that Ever Happened to NVIDIA
Edge 440: Interested in AI Evaluation? Meet Microsoft's EUREKA
Edge 439: SSMs with Attention, Understanding Zamba
AI Dropped the Mic at the Nobel Party
Edge 438: Meet DataGemma: Google DeepMind's Effort to Ground LLMs in Factual Knowledge
Edge 437: Inside BlackMamba, One of the Most Important SSM Models Ever Created
Meta Gets Into AI Video Generation
📝 Guest Post: Multimodal Retrieval –Bridging the Gap Between Language and Diverse Data Types*
Edge 436: Salesforce's xLAM is a New Model for Agentic Tasks
Edge 435: Learn About Hungry Hungry Hippos and SSMs
Edge 434: How Google DeepMind’s GameNGen can Simulate Entire 1993’s DOOM Game in Real Time
Edge 433: Samba, Unlimited Context Windows and State Space Models
The Big Bucks in Gen AI Investments
Edge 432: NVIDIA Created Minitron by Distilling Llama 3.1
Edge 431: Meet the Multimodal State Space Models
Some Non-Obvious Points About OpenAI 01
The Sequence Chat: Lewis Tunstall, Hugging Face, On Building the Model that Won the AI Math Olympiad
Edge 429: MambaByte and the Idea of Tokenization-Free SSMs
Edge 428: Inside PrompPoet: Character.ai's Framework for Prompt Engineering
Edge 427: Jamba Combines SSMs, Transformers and MOEs in a Single Model
Cerebras Inference and the Challenges of Challenging NVIDIA’s Dominance
📝 Guest Post: Will Retrieval Augmented Generation (RAG) Be Killed by Long-Context LLMs?*
Edge 426: Reviewing Google DeepMind’s New Tools for AI Interpretability and Guardrailing
Edge 425: Inside Mamba, the Most Famous SSM Model
Edge 423: Understanding the SSM Fundamental Equation
📽 [Webinar] Cut storage and processing costs for vector embeddings
Edge 422: How NuminaMath Won the AI Math Olympiad?
The Sequence Chat: Emad Mostaque -Stability AI, Schelling AI- About Open and Decentralized AI
📝 Guest Post: The Evolution of Extreme LLM Compression: From QuIP to AQLM with PV-Tuning*
Edge 421: A New Series About State Space Models
📝 Guest Post: RAG Evaluation Using Ragas*
Edge 420: Inside FlashAttention-3, The Algorithm Pushing the New Wave of Transformers
Edge 419: Everything You Need to Know About Autonomous Agents in 19 Posts
Gemma 2: A Release That Matters
📽 [Webinar] Beat GPT-4 with a Small Model and 10 Rows of Data*
Edge 418: Meet The New DSPy: The Hot Framework to Build LLM Apps You Should Know About
Edge 417: Building Multi Agent Systems
3 vs. 3: The Open vs. Closed Battle for Big AI
Edge 415: Agents that Remember Actions with Procedural Memory
📝 Guest Post: Local Agentic RAG with LangGraph and Llama 3*
One Week, 7 Major Foundation Model Releases
📽 [Virtual Talk] Supercharge Production AI with Features as Code
Edge 414: Inside Meta AI's HUSKY: A New Agent Optimized for Multi-Step Reasoning
Edge 413: Autonomous Agents and Semantic Memory
📽 [Virtual Talk] Building a Resilient, Real-Time Fraud System at Block
The Most Important Algorithm for Transformers
Edge 412: Learn About Microsoft's Impressive 4 New AI Compilers
Edge 411: Autonomous Agents with Episodic Memory
Apple Goes Small and Super Multimodal
Edge 409: Augmenting Autonomous Agents with Long-Term Memory
📝 Guest Post: Designing Prompts for LLM-as-a-Judge Model Evals*
Edge 408: Inside OpenAI's Recent Breakthroughs in GPT-4 Interpretability
Edge 407: LLMs with Infininite Context Windows? Short-Term Memory and Autonomous Agents
📽 [Virtual Talk] Powering millions of real-time rankings at GetYourGuide
Beyond OpenAI: Apple’s On-Device AI Strategy
Edge 406: Inside Anthropic's Dictionary Learning, A Breakthrough in LLM Interpretability
The Sequence Chat: Justin D. Harris - About Building Microsoft Copilot
Edge 405: Memory and Autonomous Agents
📽 [Virtual talk] Build hyper-personalized product experiences with Full RAG
Edge 403: Memory-Based Planning and Autonomous Agents
Datasets Matter: The Battle Between Open and Closed Generative AI is Not Only About Models Anymore
Edge 402: UC Berkeley's Large World Model Can Understand Really Long Videos
Edge 401: Reflection and Refinement Planning Methods in Autonomous Agents
Mistral Codestral is the Newest AI Model in the Code Generation Race
Edge 400: Inside AlphaFold 3: Google DeepMind's Amazing BioScience Model
Edge 399: Understanding External-Aid Planning and Autonomous Agents
Generative AI Unicorn Capitulation
Edge 398: Inside Phi-3: Microsoft's Amazing Small Language Model
Edge 397: Multi-Plan Selection in Autonomous Agents
[Virtual talk] How to remove the biggest blocker to production AI/ML
Reading Beyond the Hype: Some Observations About OpenAI and Google’s Announcements
Edge 395: Task Decomposition in Autonomous Agents
DeepMind’s AI-First Science Quest Continues with AlphaFold 3
Edge 393: Understanding Planning Techniques in Autonomous Agents
🔥 Announcing Galileo Protect: Real-Time Hallucination Firewall*
Maybe Two Big Research Breakthroughs or Maybe Nothing
Edge 392: Meet RAFT: UC Berkeley's New Method to Improve RAG Patterns in LLMs
Edge 391: Autonomous Agents and LLM Function Calling
Nobody Likes a Know-It-All: Smaller LLMs are Gaining Momentum
Edge 389: Understanding Large Action Models
Some Cool Details About Llama 3
Edge 388: Google DeepMind's SIMA can Follow Language Instructions in 3D Games Just Like Humans
Edge 387: Tool Learning in Autonomous Agents
Neuro-Symbolic Models are Making a Comeback
Edge 386: Inside Yi, 01's Model Leading the Chinese LLM Movement
Edge 385: The Two Big Schools for Building Autonomous Agents
Generative Audio Models Just Had a Great Week
📝 Guest Post: The EU AI Act – A Guide for Developers*
Edge 383: The Key Capabilities of Autonomous Agens
Four New Major Open Source Foundation Models in a Week
Edge 382: Google DeepMind's PrompBreeder Self-Improves Prompts
Edge 381: A New Series About Autonomous Agents
NVIDIA’s GTC in Four Headlines
📌 Exciting lineup for apply() 2024 is now live
Edge 380: Inside SELF-Discover: Google DeepMind's LLM Reasoning Method for Solving Complex Tasks
Edge 379: A Summary Of Our Series About LLM Reasoning
Explore the Global Generative AI Landscape 2024 by AIport
One AI for Navigating Any 3D Environment
📌 Exciting news! The speaker lineup for apply() 2024 is now live
Edge 378: Meet TimesFM: Google's New Foundation Model for Time-Series Forecasting
Edge 377: LLM Reasoning with Reinforced Fine-Tuning
📝 Guest Post: Evaluating LLM Applications*
📌 ML Engineering Event: Lineup for apply() 2024 is Now Live!
Edge 376: The Creators of Vicuna and Chatbot Arena Built SGLang for Super Fast LLM Inference
Edge 375: Meta's System 2 Attention is a Very Unique LLM Reasoning Method
Text-to-Video Games and 1-Bit Models: Two Monumental Generative AI Research Milestones in One Week
📌 You're invited to GenAI Productionize 2024
Edge 374: Some Technical Details we Learned About OpenAI's Sora
Edge 373: Computationally Efficient LLM Reasoning with ReWOO
Google Goes Small and Open Source with Gemma
📝 Guest Post: LoRA Land: 25 Fine-Tuned Mistral-7b LLMs that Rival or Outperform GPT-4
Edge 372: Learn About CALM, Google DeepMind's Method to Augment LLMs with Other LLMs
Edge 371: Two-Step LLM Reasoning with Skeleton of Thoughts
📌 ML Engineering Event: Mastering AI and ML at Production Scale at apply()
More Super Models is All We Need
Edge 369: LLM Reasoning with Chain-Of-Code
Don't Overlook China's Open Source LLMs
💡WEBINAR: Beyond fine-tuning. Approaches in LLM optimization
Edge 368: Inside MemGPT: A Framework for Building Autonomous Agents You Should Know About
Edge 367: Understanding Multi-Chain Reasoning in LLMs
🔥Building Plaid’s ML Fraud Detection Application—an apply() Fireside Chat
The Most Open Open Source Generative AI Release
Edge 366: Anthropic's Sleeper Agents Explore How LLMs can be Deceptive
The Sequence Pulse: The ML Architecture Powering LinkedIn's Skills Graph
Edge 365: Understanding LLM Reasoning with Reflexion
💡WEBINAR: Beyond fine-tuning. Approaches in LLM optimization
The LLMcorns: 4 New Billion Dollar Gen AI Valuations in One Week
💡On-Demand Webinar: Designing & Scaling FanDuel's Machine Learning Platform
Edge 364: About COSP and USP: Two New LLM Reasoning Methods Built by Google Research
Edge 363: Inside Google's Reasoning+Acting Method
The Model Solving Geometry Problems at the Level of a Math Olympiad Gold Medalist
📝 Guest Post: How to Build the Right Team for Generative AI*
Inside FunSearch: Google DeepMind’s LLM that Discovered New Math and Computer Science Algorithms
Edge 361: LLM Reasoning with Graph of Thoughts
A New Compute Platform for Generative AI ?
Edge 360: Meet Ghostbuster: An AI Technique for Detecting LLM-Generated Content
The Sequence Chat: Arjun Sethi on Venture Investing in Generative AI
Edge 359: Understanding Tree-Of-Thoughts in LLM Reasoning
The Transformer Robots are Here, Just a Different Kind
Edge 358: Inside AGENTS: An Open Source Framework for Autonomous Language Agents