Weights & Biases
ML experiment tracking moving into agent observability
Episodes
-
#3234: Who Should Sponsor This Podcast? Open-Book EconomicsWe open the books on our AI-generated podcast: $200/month costs, 180K plays, zero sponsors. Who should we pitch? -
#2924: When Adding One Agent Breaks EverythingThe math behind why your 100-agent pipeline fails 40% of the time — and what to do about it. -
#2254: How to Test an AI Pipeline ChangeWhen you tweak one part of a complex AI agent system, how do you know if it actually improved anything? The answer lies in engineering checkpoints. -
#1851: AI Toasters and Poetic Gym Coaches: Why We’re Drowning in Useless AIFrom smart toasters that need Wi-Fi to email rewriters that sound like corporate robots, here are the most baffling AI features we’ve seen. -
#1472: Stop Flying Your AI Agents BlindMove past basic token counting. Learn how to monitor AI reasoning, prevent $47k loops, and build trust in autonomous agents.