Uploaded April 2026 | Updated September 2026, 2 weeks ago
What are the current techniques being employed to improve the performance of LLM-based systems? How is the industry shifting from post-training towards context engineering and multi-agent orchestration? This week on the show, Jodie Burchell, data scientist and Python Advocacy Team Lead at JetBrains, returns to discuss the current AI coding landscape.
👉 Links from the show: realpython.com/podcasts/rpp/291
In our last conversation, Jodie covered how LLMs were approaching the limits of scaling laws. This time, we recap last year's big focus on reasoning models and a post-training method called "reinforcement learning from verifiable rewards" (RLVR). We also cover test-time compute, where models spend more time reasoning through steps and considering multiple approaches to solve a problem.
We touch on Agent Context Protocol (ACP), agent orchestration layers, and context engineering. We also share some concerns about the hype cycle, maintaining all that code being generated, and running local models.
- 00:00:00 -- Introduction
- 00:02:02 -- Build a Language-Learning Agent course
- 00:02:55 -- Update on the past six months of LLMs
- 00:05:32 -- Reinforcement Learning From Verifiable Rewards
- 00:07:32 -- Test Time Compute
- 00:08:36 -- 2025 and the rise of agents
- 00:14:24 -- Benchmarks shifting
- 00:15:23 -- Andrew Karpathy and jagged intelligence
- 00:19:16 -- Not evolving or growing animals but summoning ghosts
- 00:23:34 -- Diminishing gains in newer models
- 00:24:23 -- Context Engineering
- 00:35:01 -- Multi-agent systems and diversity of models
- 00:36:56 -- Video Course Spotlight
- 00:38:34 -- Current generation of coding agents
- 00:44:00 -- Fast vs deep reasoning
- 00:45:18 -- Agent Context Protocol
- 00:50:19 -- Working through the hype cycle
- 00:55:43 -- Open-source contribution pollution
- 00:57:21 -- Local models
- 00:58:36 -- Rick Beato comparing how the music industry failed
- 01:08:41 -- LLMs are an amazing development
- 01:11:33 -- Keynote talk on AI summers and winters
- 01:12:45 -- PyCon US and EuroPython
- 01:14:11 -- Thanks and goodbye
👉 Links from the show: realpython.com/podcasts/rpp/291
Download your free Python Cheat Sheet here: realpython.com/cheatsheet
Free Python Skill Test with instant level + learning plan: realpython.com/skill-test
Want to learn faster? Become a Python Expert with unlimited access to 5,000+ tutorials, videos, and exercises: realpython.com/start
🐍 Become a Python expert with real-world tutorials, on-demand courses, interactive quizzes, and 24/7 access to a community of experts at realpython.com
▰▰▰▰▰▰▰▰▰▰▰▰▰▰▰▰▰▰▰▰
🐍 Start Here → realpython.com/start
🗺️ Guided Learning Paths → realpython.com/learning-paths
🎧 Real Python Podcast → realpython.com/podcast
📚 Python Books → realpython.com/books
📖 Python Reference → realpython.com/ref
🧑💻 Quizzes & Exercises → realpython.com/quizzes
🎓 Live Courses: realpython.com/live
⭐️ Reviews & Learner Stories: realpython.com/learner-stories
▰▰▰▰▰▰▰▰▰▰▰▰▰▰▰▰▰▰▰▰
What are the current techniques being employed to improve the performance of LLM-based systems? How is the industry shifting from post-training towards context engineering and multi-agent orchestration? This week on the show, Jodie Burchell, data scientist and Python Advocacy Team Lead at JetBrains, returns to discuss the current AI coding landscape.
👉 Links from the show: realpython.com/podcasts/rpp/291
In our last conversation, Jodie covered how LLMs were approaching the limits of scaling laws. This time, we recap last year's big focus on reasoning models and a post-training method called "reinforcement learning from verifiable rewards" (RLVR). We also cover test-time compute, where models spend more time reasoning through steps and considering multiple approaches to solve a problem.
We touch on Agent Context Protocol (ACP), agent orchestration layers, and context engineering. We also share some concerns about the hype cycle, maintaining all that code being generated, and running local models.
- 00:00:00 -- Introduction
- 00:02:02 -- Build a Language-Learning Agent course
- 00:02:55 -- Update on the past six months of LLMs
- 00:05:32 -- Reinforcement Learning From Verifiable Rewards
- 00:07:32 -- Test Time Compute
- 00:08:36 -- 2025 and the rise of agents
- 00:14:24 -- Benchmarks shifting
- 00:15:23 -- Andrew Karpathy and jagged intelligence
- 00:19:16 -- Not evolving or growing animals but summoning ghosts
- 00:23:34 -- Diminishing gains in newer models
- 00:24:23 -- Context Engineering
- 00:35:01 -- Multi-agent systems and diversity of models
- 00:36:56 -- Video Course Spotlight
- 00:38:34 -- Current generation of coding agents
- 00:44:00 -- Fast vs deep reasoning
- 00:45:18 -- Agent Context Protocol
- 00:50:19 -- Working through the hype cycle
- 00:55:43 -- Open-source contribution pollution
- 00:57:21 -- Local models
- 00:58:36 -- Rick Beato comparing how the music industry failed
- 01:08:41 -- LLMs are an amazing development
- 01:11:33 -- Keynote talk on AI summers and winters
- 01:12:45 -- PyCon US and EuroPython
- 01:14:11 -- Thanks and goodbye
👉 Links from the show: realpython.com/podcasts/rpp/291
Download your free Python Cheat Sheet here: realpython.com/cheatsheet
Free Python Skill Test with instant level + learning plan: realpython.com/skill-test
Want to learn faster? Become a Python Expert with unlimited access to 5,000+ tutorials, videos, and exercises: realpython.com/start
🐍 Become a Python expert with real-world tutorials, on-demand courses, interactive quizzes, and 24/7 access to a community of experts at realpython.com
▰▰▰▰▰▰▰▰▰▰▰▰▰▰▰▰▰▰▰▰
🐍 Start Here → realpython.com/start
🗺️ Guided Learning Paths → realpython.com/learning-paths
🎧 Real Python Podcast → realpython.com/podcast
📚 Python Books → realpython.com/books
📖 Python Reference → realpython.com/ref
🧑💻 Quizzes & Exercises → realpython.com/quizzes
🎓 Live Courses: realpython.com/live
⭐️ Reviews & Learner Stories: realpython.com/learner-stories
▰▰▰▰▰▰▰▰▰▰▰▰▰▰▰▰▰▰▰▰
