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.

The RPython blog offers insights, tutorials, and updates on RPython, a subset of the Python programming language designed for writing interpreters and virtual machines. Developers can learn about RPython features, optimization techniques, and applications in building programming language implementations. Additionally, the blog covers topics such as JIT compilation, garbage collection, and static analysis using RPython, providing resources for compiler and language developers.

Real Python

A podcast episode featuring Jodie Burchell, data scientist and Python Advocacy Team Lead at JetBrains, discussing the current state of the LLM landscape. Topics include reinforcement learning from verifiable rewards (RLVR), test-time compute, the shift from post-training toward context engineering and multi-agent orchestration, Agent Context Protocol (ACP), concerns about the AI hype cycle, open-source contribution pollution from AI-generated code, and running local models. The conversation also touches on Andrej Karpathy's 'jagged intelligence' concept and the 'summoning ghosts' framing of LLMs.

Episode #291: Reassessing the LLM Landscape & Summoning Ghosts – The Real Python Podcast