Castuner

Prompt Engineering

Prompt Engineering

Practical, hype-free explainers on AI, large language models and prompt engineering from an AI/ML PhD and Google Developer Expert. Learn how to build with and get the most out of the latest AI tools. Links: Advanced RAG Course: https://prompt-s-site.thinkific.com/courses/rag Join the Patreon: https://www.patreon.com/PromptEngineering Twitter: https://twitter.com/engineerrprompt

Слушайте в своём приложении

Эпизоды

82 эпизода

  1. Harness² Explained: Self-Improving Agents Without Training 16:27
  2. Sonnet 5, more expensive than opus? 13:05
  3. DeepSeek Just Made Reasoning WAY More Efficient! 18:40
  4. Create Your OWN Web Browser with ChatGPT 7:07
  5. Wizard-Vicuna: 97% of ChatGPT - with Oobabooga Text Generation WebUI 25:55
  6. DeepSeek Just Open-Sourced How It Serves 155T Tokens a Day 22:01
  7. Web Scraping any website with ChatGPT 7:01
  8. Google's GPT-3 Moment for Time Series and Forecasting (TimesFM 3.0) 18:48
  9. BARK: BEST FREE Text-to-Audio Model 🤖🎵 | High-Quality Speech and Emotions in Multiple Languages 🎙️😂 23:51
  10. Stop Building AI Agents the Old Way 19:34
  11. Easiest Way to Convert 2D Image to 3D Animation 12:37
  12. NVIDIA's NEW INSANE "TEXT To Video" AI 12:15
  13. StableLM: Small BUT Mighty LLM | Open Source and Commerical Use 19:38
  14. Is Claude Fable 5 Worth the Hype? (Technical Deep Dive) 19:31
  15. Bonsai 27B in 3.9 GB: 1-Bit Quantization Explained and Tested 18:22
  16. Kimi K3.1 Pro and Opus 5.5 Made the Same 13 Apps (Raw Results) 31:30
  17. MiniGPT4: Open Source GPT-4 with VISION 22:17
  18. Inkling: Why Thinky's Open Model May Change "Everything" 16:06
  19. RedPajama - Llama is getting Open Source! 6:06
  20. Kimi K3 Explained! 13:12
  21. Talk to YOUR DATA without OpenAI APIs: LangChain 15:50
  22. This Tiny Engine Makes Huge AI Models Run Locally (Colibri) 17:32
  23. Test AutoGPT for FREE and Other Cool Open Source Projects 13:08
  24. Laguna S 2.1 Locally: 118B Coding Model at 80 tok/s on DGX Spark 20:46
  25. LangChain Crash Course - All You Need to Know to Build Powerful Apps with LLMs 24:24
  26. DataBricks Dolly 2.0, Commercial Use, TRUE Open Source LLM 24:43
  27. Can Kimi K3 Beat Opus 5? 13:49
  28. Huggingface Agents: Multimodal Transformers Agents Are Here and Its Open Source 27:08
  29. HUGE GPT4ALL Upgrade, CPU, Commercial License, 1-Click Install, New UI, New Base Model 12:51
  30. Qwen Calling Home? 4:51
  31. Which OPEN LLM is the BEST?? (3B to 13B models) 13:58
  32. DeepSeek V4 Flash Locally: 168 GB at 4-Bit, 25 tok/s on Two DGX Sparks 18:46
  33. Working with MULTIPLE PDF Files in LangChain: ChatGPT for your Data 12:46
  34. Qwen Just Did it Again! Open Model Is the NEW Frontier? 16:41
  35. 🤯 Spark of AGI? 🤯 AI Agents Behaving Like Humans 16:51
  36. Prime-Agent: We've Been Building AI Agents Wrong? 26:52
  37. Koala: Relatively Uncensored Vicuna/ChatGPT Alternative [Tutorial] 21:52
  38. Build a Local Router with Nemotron Lightning 18:28
  39. UNCENSORED GPT4 x Alpaca and Vicuna [Local Install + Tutorial] 18:00
  40. Distillation: What Everyone Gets Wrong! 22:41
  41. Diffusion Gemma Locally: What GPU You Need and How Fast It Runs 17:28
  42. Open Assistant: Open Source ChatGPT is Here!!! [live Demo] 22:03
  43. GPT 4 Can NOW Self Reflect Just Like Humans! 15:55
  44. GLM 5.3: The New Top Open Model! 16:23
  45. Ornith 1.0 9B vs Qwen 3.5 9B in Ollama: Same Accuracy, 3× Cheaper 16:56
  46. AUTO-GPT: Autonomous GPT-4! Mini AGI is HERE! 18:38
  47. Next Concept Models Explained: AI That Predicts Ideas, Not Words 19:28
  48. How to Use Multiple AI Agents in Your IDE 15:45
  49. MidJourney GAME Changing NEW FEATURE - /describe (Reverse Engineer PROMPTs from IMAGES) 12:14
  50. Qwen 3.8-27B in Deepseek Harness: This Is the Open-Source AI Stack to Beat 19:38