Large Language Model (LLM) Talk

Context Engineering Jan 21, 2026 00:13:58 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 outputs, and conversation history. It employs strategies like selection, compression, and

Manus AI Jan 19, 2026 00:17:12 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 excels at complex, asynchronous tasks—including app deployment, massive parallel research, and data analy

Kimi K2 Jul 22, 2025 00:15:30 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 for advanced reasoning, coding, and tool use. It offers strong performance and significantly lower pricin

Mixture-of-Recursions (MoR) Jul 18, 2025 00:16:43 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 (dynamically assigning different processing depths to individual tokens via lightweight routers), and

MeanFlow Jul 10, 2025 00:06:47 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 few-step generation using a single network evaluation. MeanFlow is built on a principled mathematical

Mamba Jul 10, 2025 00:08:14 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" information. Optimizations include a hardware-aware parallel algorithm for its recurrent

LLM Alignment Jun 14, 2025 00:20:06 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 advantageous to users. This critical process prevents unintended or harmful outputs, mitigates issues like speci

Why We Think May 20, 2025 00:14:20 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 better performance. Key approaches involve generating intermediate steps like Chain

Deep Research May 12, 2025 00:11:35 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 standard ChatGPT's single-step responses, Deep Research uses an agent architecture orchestrating specializ

vLLM May 4, 2025 00:13:06 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 blocks. This minimizes memory waste and enables flexible sharing, allowing vLLM to batch significantly m

Qwen3: Thinking Deeper, Acting Faster May 4, 2025 00:13:15 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 on a significantly expanded dataset of approximately 36 trillion tokens across 119 languages. This enhan

RAGEN: train and evaluate LLM agents using multi-turn RL May 3, 2025 00:11:56 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 analyze LLM agent training dynamics, focusing on challenges like stability, generalization, and the emerg

DeepSeek-Prover-V2 May 1, 2025 00:11:04 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 uses a two-stage training process, including supervised fine-tuning and reinforcement learning (GRPO), to

DeepSeek-Prover May 1, 2025 00:08:37 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 dataset of 8 million synthetic proofs. Quality filtering and formal verification with Lean 4 ensure data r

Model Context Protocol (MCP) Apr 9, 2025 00:13:36 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 employs a client-server architecture to overcome the complex "MxN integration problem"

LLM Post-Training: Reasoning Mar 17, 2025 00:22:18 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. Techniques like Chain-of-Thought (CoT) and Tree-of-Thoughts (ToT) prompting, along with methods like Monte Carlo

Agent AI Overview Mar 17, 2025 00:21:06 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 cross-reality training. Agent AI systems often use large foundation models (LLMs and VLMs) for enhanced perception

FlashAttention-3 Mar 7, 2025 00:13:43 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, it hides softmax latency by interleaving softmax operations with asynchronous GEMMs using techniques li

FlashAttention-2 Mar 5, 2025 00:10:50 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. A key improvement is the reduction of non-matmul FLOPs, which are less efficient on modern GPUs optimi

FlashAttention Mar 5, 2025 00:10:55 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 HBM. This contrasts with standard attention, which materializes the entire attention matrix in HBM. By min

PPO (Proximal Policy Optimization) Feb 15, 2025 00:13:42 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 and greater computational efficiency, while maintaining comparable performance. PPO approximates TRPO

"Deep Dive into LLMs like ChatGPT" - Andrej Karpathy's Tech Talk Learning Feb 15, 2025 00:18:10 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 internet text, tokenizing the text, and training neural networks to model token relationships. The

"Intro to Large Language Models" - Andrej Karpathy's Tech Talk Learning Feb 13, 2025 00:16:45 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 intensive training process, where a large amount of internet text is compressed into the model's parameters. Th

DeepSeek-V2 Feb 10, 2025 00:10:39 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 includeMulti-Head Latent Attention (MLA), which compresses the KV cache for faster inference, andDeepSeekMoE, whi

Matrix Calculus in Deep Learning Feb 10, 2025 00:11:25 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 derivative calculations in nested functions, common in neural networks. Automatic differentiation, used in

S1: Simple Test-time Scaling Feb 9, 2025 00:15:42 '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 thinking tokens by appending delimiters or the word "Wait". The s1-32B model, developed using this meth

RLHF (Reinforcement Learning from Human Feedback) Feb 7, 2025 00:15:58 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 optimizing the language model with an RL optimizer using the reward model. Techniques like KL divergence are u

GRPO (Group Relative Policy Optimization) Feb 5, 2025 00:12:31 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, unlike Proximal Policy Optimization (PPO), making it more resource efficient. It calculates advantages

Model/Knowledge Distillation Feb 5, 2025 00:14:29 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, rather than the usual "hard targets" of correct class labels. These soft targets con

Qwen-2.5 Feb 1, 2025 00:16:22 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 enhanced capacity, and Rotary Positional Embeddings (RoPE) for effective long-sequence modeling. Qwen2.

Qwen-2 Feb 1, 2025 00:13:08 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 Mixture-of-Experts (MoE) and have a reduced KV size. Pre-training data was significantly increased to 7

Qwen-1 Feb 1, 2025 00:14:43 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 Transformer architecture with untied embeddings and rotary positional embeddings. The chat models (QWE

OpenAI-o1 Jan 25, 2025 00:10:33 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 scientific and mathematical benchmarks, and is trained with a new optimization a

GPT-4o Jan 25, 2025 00:16:04 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 voice-to-voice. GPT-4o's knowledge is limited to what was available up to October 2023. It has a context

Kimi k1.5 Jan 23, 2025 00:22:27 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 and reflection without complex methods. It uses a reference policy in its off-policy RL approach, and lo

DeepSeek-R1 Jan 22, 2025 00:26:56 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 used in other algorithms such as PPO. The model uses a multi-stage training pipeline including an init

Claude-3 Jan 20, 2025 00:16:29 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, and harmless assistants and can process text, audio, and visual inputs. Claude 3 models use Constitutiona

GPT-4 Jan 20, 2025 00:11:57 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 uses a Transformer architecture, a deep learning model that has revolutionized natural language processi

LLM Training Jan 20, 2025 00:25:42 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 neural networks. The optimal model size and number of training tokens should be scaled equally, with a doub

MiniMax-01 Jan 20, 2025 00:13:23 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 offering 20-32 times longer context windows, reaching up to 4 million tokens during inference. The models

DeepSeek v3 Jan 20, 2025 00:16:01 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 auxiliary-loss-free load balancing strategy and multi-token prediction training objective. The model was pre-trained o

Tree-of-Thoughts Jan 19, 2025 00:10:08 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 evaluated using value or voting strategies, and search algorithms like breadth-first or d

LLM Reasoning Jan 19, 2025 00:23:17 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 prompts, problem decomposition, and external tools are also used. Multi-agent discussions may not surpa

LangChain Jan 18, 2025 00:19:58 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 data sources, and create applications like chatbots, question-answering systems, and virtual agents. Key

LlamaIndex Jan 18, 2025 00:25:51 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 a language model. LlamaIndex has tools to evaluate the quality of retrieval and responses. It supports

Chain of Thought (CoT) Jan 18, 2025 00:18:54 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 manageable parts, simulating human-like thought processes. This method is particularly beneficial for tasks req

Retrieval-Augmented Generation (RAG) Jan 18, 2025 00:14:26 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 matching content. The retrieved data is then passed to the LLM for response generation. This process i

Fine-Tuning Jan 18, 2025 00:23:12 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 model's performance on specialized tasks, reduce computational costs, and broaden its applicability acr

Scaling Laws Jan 17, 2025 00:09:46 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 of model size, data, and compute, and may require training large models on less data, stopping before co

LLaMA-3 Jan 17, 2025 00:20:32 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 managing complexity, using a combination of web data, code, and mathematical text, with specific pipelines for

LLaMA-2 Jan 17, 2025 00:15:03 LLaMA-2 is a collection of large language models (LLMs), with pretrained and fine-tuned versions ranging from 7 billion to 70 billion parameters. The fine-tuned models, called Llama 2-Chat, are designed for dialogue and outperform open-source models on various benchmarks. The models were trained on 2 trillion tokens of publicly available data, and were optimized for both helpfulness and safety usi

LLaMA-1 Jan 17, 2025 00:14:19 LLaMA-1 is a collection of large language models ranging from 7B to 65B parameters, trained on publicly available datasets. LLaMA models achieve competitive performance compared to other LLMs like GPT-3, Chinchilla, and PaLM, with the 13B model outperforming GPT-3 on most benchmarks, despite being much smaller, and the 65B model being competitive with the best large language models. The document a

Survey of Large Language Models Jan 17, 2025 00:12:06 The surveys of large language models (LLMs), covering their development, training, and applications. Key areas include data collection and preprocessing, which is crucial for model quality, and methods for adapting LLMs using instruction tuning or reinforcement learning with human feedback. The survey also discusses prompt engineering, which is important for task performance and involves designing

Mixture of Experts (MoE) Jan 17, 2025 00:22:04 Mixture of Experts (MoE) models use multiple sub-models, or experts, to handle different parts of the input space, orchestrated by a router or gating mechanism. MoEs are trained by dividing data, specializing experts, and using a router to direct inputs. Not all parameters are activated for each input, using sparse activation, and techniques such as load balancing and expert capacity are used to i

Multi-Task Learning Jan 16, 2025 00:22:06 Multi-task learning (MTL) is a machine learning approach where a model learns multiple tasks simultaneously, leveraging the shared information between related tasks to improve generalization. MTL can be motivated by human learning and is considered a form of inductive transfer. Two common methods for MTL in deep learning are hard and soft parameter sharing. Hard parameter sharing involves sharing

Gradient Descent Optimization Algorithms Jan 16, 2025 00:18:39 Gradient descent is a widely used optimization algorithm in machine learning and deep learning that iteratively adjusts model parameters to minimize a cost function. It operates by moving parameters in the opposite direction of the gradient. There are three main variants: batch gradient descent, which uses the whole training set; stochastic gradient descent (SGD), which uses individual training ex

GPT-1 (Generative Pre-trained Transformer) Jan 16, 2025 00:24:46 Generative Pre-trained Transformers (GPTs) are a family of large language models that use a transformer deep learning architecture. They are pre-trained on vast amounts of text data and then fine-tuned for specific tasks. GPT models can generate human-like text, translate languages, summarize content, analyze data, and write code. These models utilize self-attention mechanisms to process input and

Linear Transformers Jan 16, 2025 00:13:25 Linear Transformers address the computational limitations of standard Transformer models, which have a quadratic complexity, O(n^2), with respect to input sequence length. Linear Transformers aim for linear complexity, O(n), making them suitable for longer sequences. They achieve this through methods such as low-rank approximations, local attention, or kernelized attention. Examples include Linfor

BERT Jan 15, 2025 00:14:19 BERT (Bidirectional Encoder Representations from Transformers) is a groundbreaking NLP model from Google that learns deep, bidirectional text representations using a transformer architecture. This allows for a richer contextual understanding than previous models that only processed text unidirectionally. BERT is pre-trained using a masked language model and a next sentence prediction task on large

Sora Jan 14, 2025 00:12:41 Sora is an AI model from OpenAI that creates videos from text using a diffusion process, starting with noise and refining it. It employs a transformer architecture and handles videos as spacetime patches. Sora can extend existing footage, animate images, and blend videos. It has shown an ability to simulate elements of the real world, but has some shortcomings in depicting accurate physics and cau

Word2Vec Jan 14, 2025 00:16:01 The sources explore word embeddings, representing words as numerical vectors to capture meaning. The Skip-gram model is a key method for learning these high-quality, distributed vector representations from large text datasets. This model predicts surrounding words in a sentence, resulting in word vectors that encode linguistic patterns. To enhance the Skip-gram model, the sources introduce techniq

Stable Diffusion Jan 14, 2025 00:20:40 Diffusion models are generative models that learn to create data by reversing a process that gradually adds noise to a training sample. Stable Diffusion uses a U-Net architecture to map images to images, incorporating text prompts with CLIP embeddings and cross-attention, operating in a compressed latent space for efficiency. These models can be adapted for video generation by adding temporal laye

Retrieval Transformer Jan 14, 2025 00:14:12 The sources describe RETRO (Retrieval-Enhanced Transformer), a language model that enhances its performance by retrieving information from a large database. RETRO uses a key-value store where keys are BERT embeddings of text chunks and values are the text chunks themselves. When processing input, it retrieves similar text chunks from the database to augment the input, allowing it to perform compar

GPT-2 Jan 14, 2025 00:19:53 GPT-2 language model is a large, transformer-based model using a decoder-only architecture. It predicts the next word in a sequence, much like an advanced keyboard app. GPT-2 is auto-regressive, adding each predicted token to the input for the next step. It uses masked self-attention, focusing on previous tokens, unlike BERT's self-attention. Input tokens are processed through multiple decoder blo

GPT-3 Jan 14, 2025 00:11:59 GPT3 is a large language model that generates text based on its training on a massive dataset of 300 billion tokens. It outputs text one token at a time, influenced by input text. The model encodes what it learns in 175 billion parameters and has a context window of 2048 tokens. The core calculations happen within 96 transformer decoder layers, each with 1.8 billion parameters. Words are converted

Transformer Jan 14, 2025 00:18:51 The Transformer model is a neural network architecture that uses self-attention to understand relationships between elements in sequential data like words in a sentence. Unlike recurrent neural networks (RNNs) that process data sequentially, the Transformer can process all words in parallel. It has an encoder to read the input and a decoder to generate the output. Positional encoding accounts for

Prompt Engineering Jan 13, 2025 00:18:20 Prompt engineering is the iterative process of creating text inputs to guide AI models toward desired outputs. It involves using techniques such as clear instructions, delimiters, and specified output formats. Effective prompts may include examples, reference texts, and persona instructions. Advanced techniques like Chain-of-Thought (CoT) prompting for step-by-step reasoning, and the use of extern

Agentic AI Jan 13, 2025 00:13:02 LLM-based autonomous agents are a developing area of AI focused on creating systems that can perceive, reason, and act autonomously using large language models (LLMs). These agents use planning, memory (sensory, short-term, and long-term), and tools to accomplish tasks. They are applied in fields like social science, natural science, and engineering. Evaluation includes human assessments and objec

Episodes

Recommended