LLMs for Devs: Model Selection, Hallucinations, Agents, AGI – Jodie Burchell | The Marco Show

Video Description

Confused about which LLM: ChatGPT, Claude, or Gemini, is best for your dev projects? In this interview, Dr. Jodie Burchell, data scientist and developer advocate in data science, breaks down the LLM landscape for 2025. Discover the key criteria for choosing the best AI model: performance, cost, use-case fit, and more, so you don’t waste tokens (or your budget) on the wrong solution. What you’ll learn: – Choosing the best LLM for YOUR use case: from code generation to data analysis – How to compare LLMs – Why most AI model assessments are flawed – Enhanced vs Adaptive thinking: Is your AI model truly intelligent? – Future-proofing your developer workflow for 2025 and beyond – Privacy, self-hosting, and cost: what every developer should know – Copyright lawsuits, climate concerns, and the ethics of AI – Hallucinations, confidence, and the AI self-reinforcement loop – Will AGI arrive in the next 5 years? 🎁 Giveaway If you could name your own LLM, what would you call it? Reply in the comments. The most creative answer wins either a JetBrains merchstore coupon or a free 1-year license to your favorite JetBrains product. ⏱️ Timestamps: 00:00:00 Teaser 00:00:37 Intro 00:01:08 From PhD and academia to data science at JetBrains 00:02:31 Early NLP versus modern LLMs 00:04:46 From LSTMs to Transformers (BERT and GPT) 00:08:49 The DeepSeek surprise and model scaling limits 00:12:25 Benchmarks, assessments, and confusion for end users 00:17:18 Choosing models in practice 00:21:10 “Thinking” models and reasoning limits 00:23:48 Do you really need the newest model? 00:25:58 Hallucinations and how to handle them 00:28:30 Agents and RAG: real-world applications 00:32:55 Vibe coding: hype versus reality 00:37:46 What are AI agents? Tools, MCP, and multi-agent apps 00:43:01 Self-hosting versus proprietary models 00:45:20 Fine-tuning explained and Hugging Face 00:50:17 Building reliable AI apps (tests, A/B, traces) 00:55:33 Privacy, company data, and self-hosting concerns 00:58:37 Ethical issues: data sourcing and labor 01:04:23 Environmental costs and the push for smaller models 01:06:26 Juniors, skills, and the future of coding with AI 01:09:15 Learning fundamentals in the age of LLMs 01:13:24 AGI: definitions, timelines, and Jodie’s twenty euro bet 01:20:03 Rapid-fire questions: slang, food, and culture 01:25:47 Giveaway 01:26:26 Outro Follow Jodie Burchell: LinkedIn: https://www.linkedin.com/in/jodieburchell/ Bluesky: https://bsky.app/profile/t-redactyl.bsky.social Mastodon: https://mastodon.social/@[email protected] _______________ The Marco Show is a bi-weekly podcast about coding, developer tools, and, of course, AI. Real conversations with people who actually build things. Opposing opinions, hot takes, and practical insights. New episode every other Wednesday. Subscribe, hit the bell & never miss an episode Follow The Marco Show: Instagram: https://instagram.com/themarco.show TikTok: https://tiktok.com/@themarco.show