Applied Wizardry
Applied Wizardry is a podcast for engineers and technical founders about how AI-powered products actually get built. Host Yaniv Bernstein digs into the engineering work behind the hype, covering the practical decisions, architecture and trade-offs involved in shipping AI systems. Bernstein brings a background as a multi-time founder and engineering leader, with a PhD in computer science, ten years at Google, and executive roles at Airtasker and Vera. Episodes are aimed at builders who want substance over buzzwords.
Episodes
Death by small bugs: securing code in the Vulnpocalypse, with Patrick Collins and Simon Harloff
The frontier models that refuse to help you hack your own software are, paradoxically, making you less safe—while open weights models like DeepSeek Flash V4.1 will comply, cost a tenth as much as GPT-6, and find more vulnerabilities in the process. Patrick Collins and Simon Harloff from Dam Secure join Yaniv to explain why agent-built code needs typed languages, why PR gating has flipped from tabo
Where humans still matter when agents write the code
The traditional GitHub-style pull request review is a waste of opportunity cost for most code changes in the agentic era. Yet simply removing it without a replacement invites complexity death spirals and unbounded product behaviour that agents cannot unwind. James McGill and Haziq Nordin join Yaniv to argue that engineers should stop reading diffs line-by-line and instead scan for architectural co
12 models, one daily driver: OpenRouter's Peter Walker on how teams choose AI
Peter Walker, Head of Insights at OpenRouter and previously at Carta, sees how about 120,000 US organisations use AI models every day. He expected their usage to spread across models. Instead, the typical organisation now uses about 12 models a month, with one daily driver taking most of the tokens and specialists around it. He and Yaniv get into why, in his view, the same model can get opposite r
Cutting AI coding token costs, with Dave Slutzkin
Dave Slutzkin, co-founder of Antiburn, joins Yaniv to break down what actually drives token costs in agentic development and how to bring them down. They cover how caching differs between Anthropic and OpenAI, when to reach for which model and thinking mode, and why the habit of compaction matters more than any other optimisation. If you're spending real money on AI-assisted development, you'll co
Introducing Applied Wizardry
Applied Wizardry is a podcast for engineers and technical founders about how we build with AI: the tools, the numbers and the trade-offs, practitioner to practitioner. Hosted by Yaniv Bernstein. Episode 1, with Dave Slutzkin of Antiburn, on cutting your token burn, is out 16 October.
