Работайте офлайн с приложением Player FM !
Подкасты, которые стоит послушать
РЕКЛАМА
#24 Significantly advancing LLMs with RAG (Google's Gemini 2.0, Deep Research, notebookLM)
Manage episode 460336033 series 3585389
Dev and Doc - Latest News
Dev and Doc - Latest News
It's 2025, Dev and Doc cover the latest news including Google's deep research and notebook LM, DeepMind's Promptbreeder, and Anthropic's new RAG approach. We also go through what retrieval augmented generation (RAG) is, and how this technique is advancing LLM performance.
👋 Hey! If you are enjoying our conversations, reach out, share your thoughts and journey with us. Don't forget to subscribe whilst you're here :)
Meet the Team
Where to Follow Us
Contact Us
📧 For enquiries - Devanddoc@gmail.com
Credits
- 🎞️ Editor - Dragan Kraljević - Instagram
- 🎨 Brand Design and Art Direction - Ana Grigorovici - Behance
Episode Timeline
- 00:00 Highlights
- 00:53 News - Notebook LM, OpenAI 12 days of Christmas
- 07:44 Change in the meta - post-training
- 11:34 Optimizing prompts with DeepMind Promptbreeder
- 13:20 Is OpenAI losing their lead against Google
- 16:45 Deep research vs Perplexity
- 24:18 AIME and oncology
- 26:00 Deep research results
- 30:20 RAG intro
- 33:14 Second pass RAG
- 36:20 RAG didn't take off
- 38:40 Wikichat
- 39:16 How do we improve on RAG?
- 41:11 Semantic/topic chunking, cross-encoders, agentic RAG
- 51:15 Google’s Problem Decomposition
- 53:32 Anthropic’s Contextual Retrieval Processing
- 56:07 Summary and wrap up
References
26 эпизодов
Manage episode 460336033 series 3585389
Dev and Doc - Latest News
Dev and Doc - Latest News
It's 2025, Dev and Doc cover the latest news including Google's deep research and notebook LM, DeepMind's Promptbreeder, and Anthropic's new RAG approach. We also go through what retrieval augmented generation (RAG) is, and how this technique is advancing LLM performance.
👋 Hey! If you are enjoying our conversations, reach out, share your thoughts and journey with us. Don't forget to subscribe whilst you're here :)
Meet the Team
Where to Follow Us
Contact Us
📧 For enquiries - Devanddoc@gmail.com
Credits
- 🎞️ Editor - Dragan Kraljević - Instagram
- 🎨 Brand Design and Art Direction - Ana Grigorovici - Behance
Episode Timeline
- 00:00 Highlights
- 00:53 News - Notebook LM, OpenAI 12 days of Christmas
- 07:44 Change in the meta - post-training
- 11:34 Optimizing prompts with DeepMind Promptbreeder
- 13:20 Is OpenAI losing their lead against Google
- 16:45 Deep research vs Perplexity
- 24:18 AIME and oncology
- 26:00 Deep research results
- 30:20 RAG intro
- 33:14 Second pass RAG
- 36:20 RAG didn't take off
- 38:40 Wikichat
- 39:16 How do we improve on RAG?
- 41:11 Semantic/topic chunking, cross-encoders, agentic RAG
- 51:15 Google’s Problem Decomposition
- 53:32 Anthropic’s Contextual Retrieval Processing
- 56:07 Summary and wrap up
References
26 эпизодов
Все серии
×![Artwork](/static/images/128pixel.png)
1 #25 Testing Deepseek R1 on Complex Medical Tasks. Here's what we found. (GRPO explainer) 1:20:45
![Artwork](/static/images/128pixel.png)
1 #22 Explaining Explainable AI (for healthcare) with Dr Annabelle Painter (RSM digital health section Podcast) 58:40
![Artwork](/static/images/128pixel.png)
1 #21 Foundational Models in Digital Pathology: Enhancing Cancer detection and outcomes 1:01:43
![Artwork](/static/images/128pixel.png)
1 #20 How to build a successful healthTech/ BioTech start-up (2024 roadmap) - Derrick Khor 1:08:33
![Artwork](/static/images/128pixel.png)
1 #19 Tracking health with technology and AI - demystifying digital biomarkers 1:03:36
![Artwork](/static/images/128pixel.png)
1 #18 Keith Grimes - Startups and doctors, HealthTech consulting, Babylon's demise, Leadership theory 1:09:33
![Artwork](/static/images/128pixel.png)
1 #16 Dev&Doc x Rewired - LLMs, Clinical foundation models and automating administrative tasks (live) 46:59
![Artwork](/static/images/128pixel.png)
1 #14 Aligning AI models for healthcare | Understanding Reinforcement Learning from Human Feedback (RLHF) 42:01
![Artwork](/static/images/128pixel.png)
1 #12 2024 AI Predictions : Ambient clinical intelligence, language models as commodities, GPT-5 and AGI 46:15
Добро пожаловать в Player FM!
Player FM сканирует Интернет в поисках высококачественных подкастов, чтобы вы могли наслаждаться ими прямо сейчас. Это лучшее приложение для подкастов, которое работает на Android, iPhone и веб-странице. Зарегистрируйтесь, чтобы синхронизировать подписки на разных устройствах.