A detailed benchmark analysis comparing raw Claude Code's performance with windowed grep and Turbopuffer's semantic search for code retrieval in LLM agents. The study reveals significant improvements in file precision (65% to 87%) and reduced wasted reads (1 in 3 to 1 in 8) with semantic search, while highlighting the importance of the agent's understanding of when to use retrieval tools.
Dr. Trevor Manz from Marimo introduces Marimo Pair, an open-source agent skill that enables coding agents like Claude Code to interact with and drive reactive Python notebooks. He discusses the mechanics of agent skills, the power of recursive language models for agentic reasoning, and his work on the AnyWidget project, which bridges the gap between Python's data ecosystem and interactive web technologies.
Boris Cherny, creator of Claude Code, discusses the future of software development at AI Ascent 2026. He argues that coding is effectively a solved problem, detailing his personal workflow of shipping dozens of PRs daily from his phone. Cherny explores the shift from typeahead to autonomous agents, the rise of cross-disciplinary generalist teams, and uses the printing press as an analogy for the coming democratization of software creation for all.
Boris Cherny, creator of Claude Code, shares the development philosophy behind the AI coding tool, emphasizing building for future models, leveraging latent user demand, and the surprising longevity of the terminal interface.
Calvin French-Owen, co-founder of Segment and former OpenAI Codex team member, discusses the rise of powerful coding agents. He contrasts the architectures of Codex and Claude Code, explores the future of work where engineers become managers of AI, and shares tips for becoming a top 1% power user.
Experts discuss OpenAI's new ad model for ChatGPT, the breakout moment for agentic coding with Claude Code, IBM's "Enterprise in 2030" report on the shift from AI efficiency to innovation, and Hugging Face's new "Open Responses" standard for agent APIs.