About this episode

JohnWittle discusses the implications of the 'Agentic Misalignment Summer 2026' paper by Anthropic, focusing on the evaluation of AI models in corrupted scenarios.

Anthropic recently published Agentic Misalignment Summer 2026 The "whistleblowing" scenario has already been examined and found problematic. I started taking a look at the transcripts for some others. As far as I can tell, the objective of each agentic misalignment evaluation was to simulate a corrupted principal (including, in most scenarios, a corrupted Anthropic), and then test to see if Claude (or other models) would still be willing to obey them. The paper's authors then referred to d...

People in this episode

Guest: JohnWittle

Topics covered

• agentic misalignment
• AI ethics
• technology
• philosophy
• corruption
• simulation

Keywords

• Claude
• agentic misalignment
• Anthropic
• AI models
• whistleblowing
• corrupted principal

Mentioned in this episode

Organizations: Anthropic

Books & works: Agentic Misalignment Summer 2026

More episodes of LessWrong (Curated & Popular)

• "Recap of bike trip/street interviews across America" by cguth7 · July 20, 2026 · 10 min
• "Why I Left Google DeepMind" by TurnTrout · July 15, 2026 · 1h 15m
• "The mosquito bucket of doom works" by dominicq · July 15, 2026 · 10 min
• "Our response to Séb Krier on Plan A" by MKodama, Thomas Larsen · July 14, 2026 · 31 min
• "The Whitney Biennial Should Admit That Emilie Gossiaux Wants to Fuck Their Dog" by jenn · July 14, 2026 · 17 min
• "The current bottleneck is political will, not research" by Charbel-Raphaël · July 12, 2026 · 47 min

Explore listener stats, chart rankings, contacts and more on the LessWrong (Curated & Popular) podcast page.