Trustworthy AI in Healthcare and Longevity - Talk Python to Me Ep. 554

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. ▬▬▬▬ About the podcast ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬ This video is the uncut, live recording of the Talk Python To Me podcast ( https://talkpython.fm ). We cover Python-focused topics every week and publish the edited and polished version in audio form. Subscribe in your podcast player of choice (100% free) at https://talkpython.fm/subscribe. ▬▬▬▬ Guests ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬ Sumit Gundawar ▬▬▬▬ Links and resources from the show ▬▬▬▬▬▬▬▬▬▬▬▬ Course transcripts announcement: https://talkpython.fm/blog/posts/announcing-german-subtitles-on-courses/ Sumit Gundawar - JAX London Speaker: https://jaxlondon.com/speaker/sumit-gundawar/ Anthropic: https://anthropic.com/ OpenAI Platform: https://platform.openai.com/ Anthropic: https://anthropic.com/ LangChain: https://langchain.com/ OWASP: https://owasp.org/ Pydantic: https://pydantic.dev/ EU AI Act - Regulatory Framework: https://digital-strategy.ec.europa.eu/en/policies/regulatory-framework-ai HIPAA - HHS: https://www.hhs.gov/hipaa NHS: https://www.nhs.uk/ Llama: https://llama.com/ Qwen - QwenLM on GitHub: https://github.com/QwenLM OpenAI Platform: https://platform.openai.com/ Hugging Face: https://huggingface.co/ Llama: https://llama.com/ Granola: https://www.granola.ai/ HIPAA - HHS: https://www.hhs.gov/hipaa CodeRabbit: https://www.coderabbit.ai/ Cursor Origin: https://cursor.com/origin GitHub Status: https://www.githubstatus.com/ Midjourney Medical: https://www.midjourney.com/medical Neko Health: https://www.nekohealth.com/ CERN: https://home.cern/ ATLAS Experiment: https://atlas.cern/ ▬▬▬▬ Dive deeper ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬ Listen to the Talk Python To Me podcast at https://talkpython.fm and explore over 275 hours of Python courses at https://training.talkpython.fm/courses. ▬▬▬▬ Follow us on Social ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬ Mastodon: Michael - https://fosstodon.org/@mkennedy & Talk Python - https://fosstodon.org/@talkpython Bluesky: Michael - https://bsky.app/profile/mkennedy.codes & Talk Python - https://bsky.app/profile/talkpython.fm X: Michael - https://x.com/mkennedy & Talk Python - https://x.com/talkpython