You ask an AI a question and it answers with total confidence. Most of the time, a confidently wrong answer is just an annoyance. But what if the question is medical, and there's a real patient on the other end? In that world, a hallucination isn't a bug, it's a patient-safety event. Sumit Gundawar is a London-based software engineer who builds the clinical platform for a UK longevity and aesthetic-medicine clinic, and his whole argument is that in high-stakes AI, the model is the easy part. Earning trust is the real engineering. We dig into grounding, refusal logic, human-in-the-loop design, and the messy frontier of longevity and biohacking, plus a live demo of an assistant that refuses to answer when it can't back up the claim. Let's get into it. Episode sponsors Six Feet Up Talk Python Courses Links from the show Guest Sumit Gundawar: linkedin.com Course transcripts announcement: talkpython.fm/blog Sumit Gundawar - JAX London Speaker: jaxlondon.com Anthropic: anthropic.com OpenAI Platform: platform.openai.com Anthropic: anthropic.com LangChain: langchain.com OWASP: owasp.org Pydantic: pydantic.dev EU AI Act - Regulatory Framework: digital-strategy.ec.europa.eu HIPAA - HHS: www.hhs.gov NHS: www.nhs.uk Llama: llama.com Qwen - QwenLM on GitHub: github.com OpenAI Platform: platform.openai.com Hugging Face: huggingface.co Llama: llama.com Granola: www.granola.ai HIPAA - HHS: www.hhs.gov CodeRabbit: www.coderabbit.ai Cursor Origin: cursor.com GitHub Status: www.githubstatus.com Midjourney Medical: www.midjourney.com Neko Health: www.nekohealth.com CERN: home.cern ATLAS Experiment: atlas.cern Watch this episode on YouTube: youtube.com Episode #554 deep-dive: talkpython.fm/554 Episode transcripts: talkpython.fm Theme Song: Developer Rap 🥁 Served in a Flask 🎸: talkpython.fm/flasksong ---== Don't be a stranger ==--- YouTube: youtube.com/@talkpython Bluesky: @talkpython.fm Mastodon: @talkpython@fosstodon.org X.com: @talkpython Michael on Bluesky: @mkennedy.codes Michael on Mastodon: @mkennedy@fosstodon.org Michael on X.com: @mkennedy
Software Engineer
Analysis: done · source seed