Large Language Model (LLM) Talk
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.
Categories: Technology
Listen to the last episode:
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 ordering to manage token limits and prevent "context rot." By orchestrating how information is filtered and presented at runtime, context engineering ensures LLMs remain grounded and reliable for complex, long-horizon tasks, effectively serving as the operating system for agentic AI.
Previous episodes
-
68 - Context Engineering Wed, 21 Jan 2026
-
67 - Manus AI Mon, 19 Jan 2026
-
66 - Kimi K2 Tue, 22 Jul 2025
-
65 - Mixture-of-Recursions (MoR) Fri, 18 Jul 2025
-
64 - MeanFlow Thu, 10 Jul 2025
-
63 - Mamba Thu, 10 Jul 2025
-
62 - LLM Alignment  Sat, 14 Jun 2025
-
61 - Why We Think Tue, 20 May 2025
-
60 - Deep Research Mon, 12 May 2025
-
59 - vLLM Sun, 04 May 2025
-
58 - Qwen3: Thinking Deeper, Acting Faster Sun, 04 May 2025
-
57 - RAGEN: train and evaluate LLM agents using multi-turn RL Sat, 03 May 2025
-
56 - DeepSeek-Prover-V2 Thu, 01 May 2025
-
55 - DeepSeek-Prover Thu, 01 May 2025
-
54 - Model Context Protocol (MCP) Wed, 09 Apr 2025
-
53 - LLM Post-Training: Reasoning Mon, 17 Mar 2025
-
52 - Agent AI Overview Mon, 17 Mar 2025
-
51 - FlashAttention-3 Fri, 07 Mar 2025
-
50 - FlashAttention-2 Wed, 05 Mar 2025
-
49 - FlashAttention Wed, 05 Mar 2025
-
48 - PPO (Proximal Policy Optimization) Sat, 15 Feb 2025
-
47 - "Deep Dive into LLMs like ChatGPT" - Andrej Karpathy's Tech Talk Learning Sat, 15 Feb 2025
-
46 - "Intro to Large Language Models" - Andrej Karpathy's Tech Talk Learning Thu, 13 Feb 2025
-
45 - DeepSeek-V2 Mon, 10 Feb 2025
-
44 - Matrix Calculus in Deep Learning Mon, 10 Feb 2025
-
43 - S1: Simple Test-time Scaling Sun, 09 Feb 2025
-
42 - RLHF (Reinforcement Learning from Human Feedback) Fri, 07 Feb 2025
-
41 - GRPO (Group Relative Policy Optimization) Wed, 05 Feb 2025
-
40 - Model/Knowledge Distillation Wed, 05 Feb 2025
-
39 - Qwen-2.5 Sat, 01 Feb 2025
-
38 - Qwen-2 Sat, 01 Feb 2025
-
37 - Qwen-1 Sat, 01 Feb 2025
-
36 - OpenAI-o1 Sat, 25 Jan 2025
-
35 - GPT-4o Sat, 25 Jan 2025
-
34 - Kimi k1.5 Thu, 23 Jan 2025
-
33 - DeepSeek-R1 Wed, 22 Jan 2025
-
32 - Claude-3 Mon, 20 Jan 2025
-
31 - GPT-4 Mon, 20 Jan 2025
-
30 - LLM Training Mon, 20 Jan 2025
-
29 - MiniMax-01 Mon, 20 Jan 2025
-
28 - DeepSeek v3 Mon, 20 Jan 2025
-
27 - Tree-of-Thoughts Sun, 19 Jan 2025
-
26 - LLM Reasoning Sun, 19 Jan 2025
-
25 - LangChain Sat, 18 Jan 2025
-
24 - LlamaIndex Sat, 18 Jan 2025
-
23 - Chain of Thought (CoT) Sat, 18 Jan 2025
-
22 - Retrieval-Augmented Generation (RAG) Sat, 18 Jan 2025
-
21 - Fine-Tuning Sat, 18 Jan 2025
-
20 - Scaling Laws Fri, 17 Jan 2025
-
19 - LLaMA-3 Fri, 17 Jan 2025