PODCAST · technology
Large Language Model (LLM) Talk
by AI-Talk
AI Explained breaks down the world of AI in just 10 minutes. Get quick, clear insights into AI concepts and innovations, without any complicated math or jargon. Perfect for your commute or spare time, this podcast makes understanding AI easy, engaging, and fun—whether you're a beginner or tech enthusiast.
Episodes
-
Context Engineering
Context engineering is the system-level discipline of architecting the dynamic information environment for AI models. Unlike prompt engineering, which focuses on phrasing specific instructions, context engineering programmatically assembles the model's "working memory" using retrieved data, tool...
-
Manus AI
Manus AI is a general-purpose autonomous agent designed to function as a digital worker rather than a passive chatbot. Developed by Monica and acquired by Meta, it utilizes a Planner-Executor architecture to orchestrate foundation models like Claude and Qwen within cloud-based sandboxes. Manus...
-
Kimi K2
Kimi K2, developed by Moonshot AI, is an open agentic intelligence model built on a Mixture-of-Experts (MoE) architecture. It features 1 trillion total parameters, with 32 billion active during inference. Trained on 15.5 trillion tokens using the stable MuonClip optimizer, Kimi K2 is optimized…
more -
Mixture-of-Recursions (MoR)
Mixture-of-Recursions (MoR) is a unified framework built on a Recursive Transformer architecture, designed to enhance the efficiency of large language models. It achieves this by combining three core paradigms: parameter sharing (reusing shared layers across recursion steps), adaptive computation...
-
MeanFlow
MeanFlow models introduce the concept of average velocity to fundamentally reformulate one-step generative modeling. Unlike Flow Matching, which focuses on instantaneous velocity, MeanFlow directly models the displacement over a time interval. This approach allows for highly efficient one-step or...
-
Mamba
Mamba is a novel deep learning architecture that achieves linear scaling in computation and memory with sequence length, addressing Transformers' quadratic limitations. Its selective State Space Model (SSM) layer dynamically adapts to input context, allowing it to "forget" or "remember"...
-
LLM Alignment
LLM alignment is the process of steering Large Language Models to operate in a manner consistent with intended human goals, preferences, and ethical principles. Its primary objective is to make LLMs helpful, honest, and harmless, ensuring their outputs align with specific values and are...
-
Why We Think
The "Why We Think" from Lilian Weng, examines improving language models by allocating more computation at test time, drawing an analogy to human "slow thinking" or System 2. By treating computation as a resource, the aim is to design systems that can utilize this test-time effort effectively for...
-
Deep Research
Deep Research is an autonomous research agent built into ChatGPT. It performs multi-step online research over several minutes, behaving like a human researcher by searching, reading, analyzing, and synthesizing information from multiple sources. It produces detailed, cited reports. Unlike…
more -
vLLM
vLLM is a high-throughput serving system for large language models. It addresses inefficient KV cache memory management in existing systems caused by fragmentation and lack of sharing, which limits batch size. vLLM uses PagedAttention, inspired by OS paging, to manage KV cache in non-contiguous...
-
Qwen3: Thinking Deeper, Acting Faster
Qwen3 models introduce both Mixture-of-Experts (MoE) and dense architectures. They utilize hybrid thinking modes, allowing users to balance response speed and reasoning depth for tasks, controllable via parameters or tags. Developed through a multi-stage post-training pipeline, Qwen3 is trained…
more -
RAGEN: train and evaluate LLM agents using multi-turn RL
RAGEN is a modular system for training and evaluating LLM agents using multi-turn reinforcement learning. Built on the StarPO framework, it implements the full training loop including rollout generation, reward assignment, and trajectory optimization. RAGEN serves as research infrastructure to...
-
DeepSeek-Prover-V2
DeepSeek-Prover-V2 is an open-source large language model designed for formal theorem proving in Lean 4. Its training relies heavily on synthetic data, generated by using DeepSeek-V3 to decompose problems into subgoals, which are then recursively solved by a smaller 7B prover model. The model…
more -
DeepSeek-Prover
The DeepSeek-Prover project aims to advance large language model capabilities in formal theorem proving by addressing the scarcity of training data. It uses autoformalization to convert informal high school and undergraduate math competition problems into formal statements, generating a large...
-
Model Context Protocol (MCP)
The Model Context Protocol (MCP), introduced by Anthropic in November 2024, is an open protocol standardizing how applications provide context to LLMs. Acting like a "USB-C port for AI applications," it provides a standardized way to connect AI models to different data sources and tools. MCP...
-
LLM Post-Training: Reasoning
LLM post-training is crucial for refining the reasoning abilities developed during pretraining. It employs fine-tuning on specific reasoning tasks, reinforcement learning to reward logical steps and coherent thought processes, and test-time scaling to enhance reasoning during inference.…
more -
Agent AI Overview
Agent AI refers to interactive systems that perceive visual, language, and environmental data to produce meaningful embodied actions in physical and virtual worlds. It aims to create sophisticated and context-aware AI, potentially paving the way for AGI by leveraging generative AI and…
more -
FlashAttention-3
FlashAttention-3 accelerates attention on NVIDIA Hopper GPUs through three key innovations. It achieves producer-consumer asynchrony by dividing warps into producer (data loading with TMA) and consumer (computation with asynchronous Tensor Cores) roles, overlapping these critical phases. Second…
more -
FlashAttention-2
FlashAttention-2 builds upon FlashAttention to achieve faster attention computation with better GPU resource utilization. It enhances parallelism by also parallelizing along the sequence length dimension, optimizing work partitioning between thread blocks and warps to reduce shared memory access.…
more -
FlashAttention
FlashAttention is an IO-aware attention mechanism designed to be fast and memory-efficient, especially for long sequences. Its core innovation is tiling, where input sequences are divided into blocks processed within the fast on-chip SRAM, significantly reducing reads and writes to the slower…
more -
PPO (Proximal Policy Optimization)
PPO (Proximal Policy Optimization) is a reinforcement learning algorithm that balances simplicity, stability, sample efficiency, general applicability, and strong performance. PPO replaced TRPO (Trust Region Policy Optimization) as the default algorithm at OpenAI due to its simpler implementation...
-
"Deep Dive into LLMs like ChatGPT" - Andrej Karpathy's Tech Talk Learning
Andrej Karpathy's tech talk (youtube), provides a comprehensive yet accessible overview of Large Language Models (LLMs) like ChatGPT. The talk details the process of building an LLM, including pre-training, data processing, and neural network training.Key stages include downloading and filtering...
-
"Intro to Large Language Models" - Andrej Karpathy's Tech Talk Learning
Andrej Karpathy's talk, "Intro to Large Language Models," demystifies LLMs by portraying them as systems with two key components:a parameters file (the weights of the neural network) anda run file (the code that runs the network). The creation of these files starts with a computationally…
more -
DeepSeek-V2
DeepSeek-V2 is a Mixture-of-Experts (MoE) language model that balances strong performance with economical training and efficient inference. It uses a total of 236B parameters, with 21B activated for each token, and supports a context length of 128K tokens. Key architectural innovations...
-
Matrix Calculus in Deep Learning
Matrix calculus is essential for understanding and implementing deep learning. It provides the mathematical tools to optimize neural networks using gradient descent. The Jacobian matrix, a key concept, organizes partial derivatives of vector-valued functions. The vector chain rule simplifies...
-
S1: Simple Test-time Scaling
'S1' refers to simple test-time scaling, an efficient approach to enhance language model reasoning with minimal resources. It involves training a model on a small, carefully curated dataset like s1K and using budget forcing to control test-time compute. Budget forcing enforces maximum or minimum...
-
RLHF (Reinforcement Learning from Human Feedback)
Reinforcement Learning from Human Feedback (RLHF) incorporates human preferences into AI systems, addressing problems where specifying a clear reward function is difficult. The basic pipeline involves training a language model, collecting human preference data to train a reward model, and...
-
GRPO (Group Relative Policy Optimization)
Group Relative Policy Optimization (GRPO) is a reinforcement learning algorithm that enhances mathematical reasoning in large language models (LLMs). It is like training students in a study group, where they learn by comparing answers without a tutor. GRPO eliminates the need for a critic model,...
-
Model/Knowledge Distillation
Model/Knowledge distillation is a technique to transfer knowledge from a cumbersome model, like a large neural network or an ensemble of models, to a smaller, more efficient model. The smaller model is trained using "soft targets," which are the class probabilities produced by the larger model,...
-
Qwen-2.5
Qwen2.5 is a series of large language models (LLMs) with significant improvements over previous models, focusing on efficiency, performance, and long sequence handling. Key architectural advancements include Grouped Query Attention (GQA) for better memory management, Mixture-of-Experts (MoE) for...
-
Qwen-2
The Qwen2 series of large language models introduces several key enhancements over its predecessors. It employs Grouped Query Attention (GQA) and Dual Chunk Attention (DCA) for improved efficiency and long-context handling, using YARN to rescale attention weights. The models utilize fine-grained...
-
Qwen-1
Qwen-1, also known as QWEN, is a series of large language models that includes base pretrained models, chat models, and specialized models for coding and math. These models are trained on a massive dataset of 3 trillion tokens using byte pair encoding for tokenization, and they feature a modified...
-
OpenAI-o1
OpenAI's o1 is a generative pre-trained transformer (GPT) model, designed for enhanced reasoning, especially in science and math. It uses a 'chain of thought' approach, spending more time "thinking" before answering, making it better at complex tasks. While not a successor to GPT-4o, o1 excels in...
-
GPT-4o
GPT-4o is a multilingual, multimodal model that can process and generate text, images, and audio and represents a significant advancement over previous models like GPT-4 and GPT-3.5. GPT-4o is faster and more cost-effective, has improved performance in multiple areas, and natively supports...
-
Kimi k1.5
Kimi k1.5 is a multimodal LLM trained with reinforcement learning (RL). Key aspects include: long context scaling to 128k, improving performance with increased context length; improved policy optimization using a variant of online mirror descent; and a simplistic framework that enables planning…
more -
DeepSeek-R1
DeepSeek-R1 is a language model focused on enhanced reasoning, employing reinforcement learning (RL) and building upon the DeepSeek-V3-Base model. It uses Group Relative Policy Optimization (GRPO) to reduce computational costs by eliminating the need for a separate critic model, which is commonly...
-
Claude-3
Claude 3 is a family of large multimodal AI models developed by Anthropic, with a focus on safety, interpretability, and user alignment. The models, which include Opus, Sonnet, and Haiku, excel in reasoning, math, coding, and multilingual understanding. They are designed to be helpful, honest…
more -
GPT-4
GPT-4, or Generative Pre-trained Transformer 4, is a large multimodal language model created by OpenAI, and the fourth in the GPT series. It is a significant advancement over previous models such as GPT-3, with improvements in model size, performance, contextual understanding, and safety. GPT-4...
-
LLM Training
Training large language models (LLMs) is challenging due to the large amount of GPU memory and long training times required. Several parallelism paradigms enable model training across multiple GPUs, and various model architecture and memory-saving designs make it possible to train very large…
more -
MiniMax-01
MiniMax-01 is a series of large language and vision-language models that use lightning attention and a mixture of experts (MoE) to achieve long context processing. The models, MiniMax-Text-01 and MiniMax-VL-01, match the performance of top-tier models, like GPT-4o and Claude-3.5-Sonnet, while...
-
DeepSeek v3
DeepSeek-V3 is a large Mixture-of-Experts (MoE) language model, trained ~10x less cost, with 671 billion total parameters, of which 37 billion are activated for each token. It uses Multi-head Latent Attention (MLA) and DeepSeekMoE architectures. A key feature of DeepSeek-V3 is its...
-
Tree-of-Thoughts
The Tree of Thoughts (ToT) framework enhances problem-solving in large language models (LLMs) by using a structured, hierarchical approach to explore multiple solutions. ToT breaks down problems into smaller steps called "thoughts", generated via sampling or proposing. These "thoughts" are...
-
LLM Reasoning
Large language models (LLMs) demonstrate some reasoning abilities, though it's debated whether they truly reason or rely on information retrieval. Prompt engineering enhances reasoning, employing techniques like Chain-of-Thought (CoT), which involves intermediate reasoning steps. Multi-stage...
-
LangChain
LangChain is an open-source framework that simplifies the development of applications using large language models (LLMs). It offers tools and abstractions to enhance the customization, accuracy, and relevancy of LLM-generated information. LangChain allows developers to connect LLMs to external…
more -
LlamaIndex
LlamaIndex is an open-source framework for building LLM applications by connecting custom data to LLMs. It excels in Retrieval-Augmented Generation (RAG), data storage, and retrieval. It works by ingesting data from various sources, indexing it (often into vector embeddings), and querying it with…
more -
Chain of Thought (CoT)
Chain of Thought (CoT) is a prompting technique that enhances the reasoning capabilities of large language models (LLMs) by encouraging them to articulate their reasoning process step by step. Instead of providing a direct answer, the model breaks down complex problems into smaller, more…
more -
Retrieval-Augmented Generation (RAG)
Retrieval-augmented generation (RAG) enhances large language models (LLMs) by connecting them to external knowledge sources. It works by retrieving relevant documents based on a user's query, using an embedding model to convert both into numerical vectors, then using a vector database to find...
-
Fine-Tuning
Fine-tuning is a machine learning technique that adapts a pre-trained model to a specific task or domain. Instead of training a model from scratch, fine-tuning uses a pre-trained model as a starting point and further trains it on a smaller, task-specific dataset. This process can improve the...
-
Scaling Laws
Scaling laws describe how language model performance improves with increased model size, training data, and compute. These improvements often follow a power-law, with predictable gains as resources scale up. There are diminishing returns with increased scale. Optimal training involves a balance…
more -
LLaMA-3
LLaMA-3 is a series of foundation language models that support multilinguality, coding, reasoning, and tool usage. The models come in different sizes, with the largest having 405B parameters and a 128K token context window. The development of Llama 3 focused on optimizing data, scale, and…
more
We're indexing this podcast's transcripts for the first time — this can take a minute or two. We'll show results as soon as they're ready.
No matches for "" in this podcast's transcripts.
No topics indexed yet for this podcast.
Loading reviews...
ABOUT THIS SHOW
AI Explained breaks down the world of AI in just 10 minutes. Get quick, clear insights into AI concepts and innovations, without any complicated math or jargon. Perfect for your commute or spare time, this podcast makes understanding AI easy, engaging, and fun—whether you're a beginner or tech enthusiast.
HOSTED BY
AI-Talk
CATEGORIES
Loading similar podcasts...
Frequently Asked Questions
How many episodes does Large Language Model (LLM) Talk have?
Large Language Model (LLM) Talk currently has 68 episodes available on PodParley. New episodes are automatically indexed when they're published to the podcast feed.
What is Large Language Model (LLM) Talk about?
AI Explained breaks down the world of AI in just 10 minutes. Get quick, clear insights into AI concepts and innovations, without any complicated math or jargon. Perfect for your commute or spare time, this podcast makes understanding AI easy, engaging, and fun—whether you're a beginner or tech...
How often does Large Language Model (LLM) Talk release new episodes?
Large Language Model (LLM) Talk has 68 episodes. Check the episode list to see recent publication dates and frequency.
Where can I listen to Large Language Model (LLM) Talk?
You can listen to Large Language Model (LLM) Talk on PodParley by clicking any episode. We provide an embedded audio player for direct listening, and you can also subscribe via your preferred podcast app using the RSS feed.
Who hosts Large Language Model (LLM) Talk?
Large Language Model (LLM) Talk is created and hosted by AI-Talk.
URL copied to clipboard!