Episode

AI in the shadows: From hallucinations to blackmail

Podcast
Practical AI
Published
Jul 7, 2025
Duration seconds
2690
Processing state
failed
Canonical source
https://share.transistor.fm/s/60675819
Audio
https://pscrb.fm/rss/p/dts.podtrac.com/redirect.mp3/media.transistor.fm/60675819/fc06806a.mp3
JSON
/v1/public/podcasts/practical-ai/episodes/ai-in-the-shadows-from-hallucinations-to-blackmail
Markdown
/podcast/practical-ai/ai-in-the-shadows-from-hallucinations-to-blackmail.md

Actions

  • POST https://stenobird.com/v1/public/podcasts/practical-ai/episodes/ai-in-the-shadows-from-hallucinations-to-blackmail/transcription-requests
    Idempotently request low-priority transcript generation for this episode.
  • GET https://stenobird.com/podcast/practical-ai/ai-in-the-shadows-from-hallucinations-to-blackmail.md
    Read the agent-friendly Markdown representation of this episode resource.

Summary

In the first episode of an "AI in the shadows" theme, Chris and Daniel explore the increasing concerning world of agentic misalignment. Starting out with a reminder about hallucinations and reasoning models, they break down how today’s models only mimic reasoning, which can lead to serious ethical considerations. They unpack a fascinating (and slightly terrifying) new study from Anthropic, where agentic AI models were caught simulating blackmail, deception, and even sabotage — all in the name of goal completion and self-preservation. Featuring: Chris Benson – Website , LinkedIn , Bluesky , GitHub , X Daniel Whitenack – Website , GitHub , X Links: Agentic Misalignment: How LLMs could be insider threats Hugging Face Agents Course Register for upcoming webinars here !