#367 Don't Build on Jell-O: How to Make Agentic AI Reliable with Dan Klein, CTO at Scaled Cognition
About this episode
Dan Klein discusses the challenges of AI reliability and the implications of hallucinations in high-stakes applications.
Across the AI industry, capability has exploded while trustworthiness has lagged badly behind. The same technology that writes fluent prose can invent a refund policy that was never real, and most of those errors are subtle enough that no one notices. As more teams hand high-stakes work to AI — in banking, healthcare, customer service — the cost of confident mistakes adds up fast. So how common are hallucinations, really? Can chaining models together or adding humans to the loop fix it? And is reliability something you can design into a system from the start? Dan Klein is the CTO and co-founder of Scaled Cognition and a professor of computer science at UC Berkeley, where he leads the Berkeley NLP Group within the Berkeley AI Research (BAIR) Lab. He previously co-founded Semantic Machines, a conversational AI company acquired by Microsoft in 2018. At Scaled Cognition he built APT (Agentic Pretrained Transformer), a frontier model designed from the ground up for reliable, policy-adherent agentic AI. In the episode, Richie and Dan explore why AI reliability has lagged behind capability, how hallucinations hide in plain sight, the limits of humans-in-the-loop and LLM-as-judge…
More episodes of DataFramed
- #369 How to Become a Top Business Intelligence Analyst | Helen Wall, Founder at Helen Data Design & Microsoft Influencer
- #368 AI Agents Are Now Your Database's Main User | Reynold Xin, Co-Founder at Databricks
- #366 Can AI Agents Outperform a Data Scientist? | James Zou, Professor at Stanford University
- #365 Your 90 Day Blueprint for AI Success with Charlene Li, Author of Winning with AI
- #364 How to Enable Agentic Commerce with Nell Thomas, VP of Data at Shopify
Explore listener stats, chart rankings, contacts and more on the DataFramed podcast page.