Episode

Why LLMs Are Plausibility Engines, Not Truth Engines | Dan Klein

Podcast
Chain of Thought | AI Agents, Infrastructure & Engineering
Published
Apr 8, 2026
Duration seconds
4693
Processing state
not_requested
Canonical source
https://share.transistor.fm/s/9ab75e81
Audio
https://media.transistor.fm/9ab75e81/8f5187a8.mp3
JSON
/v1/public/podcasts/chain-of-thought-ai-agents/episodes/why-llms-are-plausibility-engines-not-truth-engines-dan-klein
Markdown
/podcast/chain-of-thought-ai-agents/why-llms-are-plausibility-engines-not-truth-engines-dan-klein.md

Actions

  • POST https://stenobird.com/v1/public/podcasts/chain-of-thought-ai-agents/episodes/why-llms-are-plausibility-engines-not-truth-engines-dan-klein/transcription-requests
    Idempotently request low-priority transcript generation for this episode.
  • GET https://stenobird.com/podcast/chain-of-thought-ai-agents/why-llms-are-plausibility-engines-not-truth-engines-dan-klein.md
    Read the agent-friendly Markdown representation of this episode resource.

Summary

Dan Klein, co-founder & CTO of Scaled Cognition and ACM Grace Murray Hopper Award winner, breaks down why LLMs are fundamentally plausibility engines and how his team built APT1 for under 11 million dollars. He explains why multi-model checking fails, why benchmarks measure the wrong thing, and what it takes to ship AI that enterprises can actually trust.