About this podcast
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
The newest 20 of 68 episodes
- Context Engineering · 14 minContext engineering is the system-level discipline of architecting the dynamic information environment for AI models. Unlike prompt engineering, which focuses on phrasing…
- Manus AI · 17 minManus 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…
- Kimi K2 · 16 minKimi 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…
- Mixture-of-Recursions (MoR) · 17 minMixture-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…
- MeanFlow · 7 minMeanFlow models introduce the concept of average velocity to fundamentally reformulate one-step generative modeling. Unlike Flow Matching, which focuses on instantaneous…
- Mamba · 8 minMamba is a novel deep learning architecture that achieves linear scaling in computation and memory with sequence length, addressing Transformers' quadratic limitations. Its…
- LLM Alignment · 20 minLLM 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…
- Why We Think · 14 minThe "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…
- Deep Research · 12 minDeep 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…
- vLLM · 13 minvLLM 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…
- Qwen3: Thinking Deeper, Acting Faster · 13 minQwen3 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…
- RAGEN: train and evaluate LLM agents using multi-turn RL · 12 minRAGEN 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…
- DeepSeek-Prover-V2 · 11 minDeepSeek-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-Prover · 9 minThe 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…
- Model Context Protocol (MCP) · 14 minThe 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…
- LLM Post-Training: Reasoning · 22 minLLM post-training is crucial for refining the reasoning abilities developed during pretraining. It employs fine-tuning on specific reasoning tasks, reinforcement learning to…
- Agent AI Overview · 21 minAgent 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…
- FlashAttention-3 · 14 minFlashAttention-3 accelerates attention on NVIDIA Hopper GPUs through three key innovations. It achieves producer-consumer asynchrony by dividing warps into producer (data loading…
- FlashAttention-2 · 11 minFlashAttention-2 builds upon FlashAttention to achieve faster attention computation with better GPU resource utilization. It enhances parallelism by also parallelizing along the…
- FlashAttention · 11 minFlashAttention 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…
