EPISODE · Jul 7, 2025 · 44 MIN
AI in the shadows: From hallucinations to blackmail
from Practical AI · host Practical AI LLC
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, XDaniel Whitenack – Website, GitHub, XLinks:Agentic Misalignment: How LLMs could be insider threatsHugging Face Agents CourseRegister for upcoming webinars here!
What this episode covers
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, XDaniel Whitenack – Website, GitHub, XLinks:Agentic Misalignment: How LLMs could be insider threatsHugging Face Agents CourseRegister for upcoming webinars here!
NOW PLAYING
AI in the shadows: From hallucinations to blackmail
No transcript for this episode yet
Similar Episodes
Apr 21, 2026 ·13m
Apr 19, 2026 ·16m
Apr 17, 2026 ·13m
Apr 13, 2026 ·11m
Apr 11, 2026 ·16m