The Monkey Patching Podcast: Going Bananas on AI, Data, LLMs & Tech

Thanks for listening! Subscribe and follow wherever you get your podcasts.Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 tokens/sec — Hacker News Fast Apply from Morph promises near-instant AI patches, aiming to replace sluggish full-file rewrites with surgical edits. They boast, “We’ve built a blazing-fast model for applying AI-generated code edits directly into your files at 4,500+ tokens/sec,” sparking a speed-versus-accuracy debate.

Thanks for listening, leave a review! ❤️The New Skill in AI is Not Prompting, It's Context Engineering | Phil Schmid Blog (Jun 30 2025) Phil Schmid argues that the real differentiator in modern AI work is “context engineering,” the discipline of assembling the right information, tools and format around an LLM rather than obsessing over single-string prompts. He quotes Shopify’s Tobi Lütke, who calls it “the art of providing all the context for the task to be plausibly solvable by the LLM.”

Thanks for listening! Make sure to leave a review ❤️Serena: A powerful coding agent toolkit | GitHub Serena presents itself as a full-featured coding agent that melds semantic code search, automated editing and shell execution to streamline developer workflows. “Serena combines tools for semantic code retrieval with editing capabilities and shell execution.” 🔗 https://github.com/oraios/serenaNxtscape – an open-source agentic browser | nxtscape.ai Nxtscape pitches a privacy-first browser

Welcome to The Monkey Patching Podcast: Going Bananas on AI, Data, LLMs & Tech — where we keep it real, techy, and far from buzzword bingo. Tune in wherever you get your podcasts, or visit us at monkeypatching.io🧠 Episode Topics & LinksYour Brain on ChatGPT: Accumulation of Cognitive Debt when Using an AI Assistant for Essay Writing Task New arXiv research shows relying on ChatGPT dulls neural engagement and weakens writing skills compared to search or free writing. EEG readings

Welcome to Episode 2!We'd love to hear your feedback ❤️  DuckLake: SQL as a Lakehouse Format | DuckDB Blog (May 27 2025)DuckDB’s new DuckLake format proposes shifting all lakehouse metadata into a regular SQL database so open-format data lakes can gain true transactional speed and simplicity. “DuckLake re-imagines what a ‘Lakehouse’ format should look like,” the authors write, arguing it eliminates the maze of JSON files and external catalog services. If adopted, DuckLake could let

Hey there! Welcome to the very first Monkey Patching Podcast. We're just kicking things off today, chatting about what we've got planned for this show – nothing too mind-blowing yet, but we're excited to get rolling. If you're into data and AI talk without all the buzzword fluff, hit subscribe and join us for the ride. Trust us, it gets better from here.Ow yeah... while we said that we would start numbering at 0, our podcast hosting platform doesn't support it 🙈Thanks for listening!Much