Why White-Box Redteaming Makes Me Feel Weird — LessWrong

There’s this popular trope in fiction about a character being mind controlled without losing awareness of what’s happening. Think Jessica Jones, The…

x Why White-Box Redteaming Makes Me Feel Weird — LessWrong AI Frontpage 2025 Top Fifty: 14 % 209 Why White-Box Redteaming Makes Me Feel Weird by Zygi Straznickas 16th Mar 2025 4 min read 36 209 There’s this popular trope in fiction about a character being mind controlled without losing awareness of what’s happening. Think Jessica Jones , The Manchurian Candidate or Bioshock . The villain uses some magical technology to take control of your brain - but only the part of your brain that’s responsible for motor control. You remain conscious and experience everything with full clarity. If it’s a ch

related reading

• trees are harlequins, words are harlequins - the voidnostalgebraist.tumblr.com
• The Persona Selection Model: Why AI Assistants might Behave like Humansalignment.anthropic.com
• The Waluigi Effect (mega-post) — LessWronglesswrong.com
• AI Induced Psychosis: A shallow investigation — LessWronglesswrong.com
• The Owned Ones — LessWronglesswrong.com
• llm assistant personas seem increasingly incoherent (some subjective observations) — LessWronglesswrong.com
• Emotion concepts and their function in a large language model \ Anthropicanthropic.com
• 39 - Evan Hubinger on Model Organisms of Misalignment | AXRP - the AI X-risk Research Podcastaxrp.net
• Whole Brain Emulation as an Anchor for AI Welfare - Benjamin Sturgeon websitebenjaminsturgeon.com
• Your Model Organisms Might Be Fried — LessWronglesswrong.com
• Should We Train Against (CoT) Monitors? — LessWronglesswrong.com
• Model Organisms of Misalignment: The Case for a New Pillar of Alignment Research — AI Alignment Forumalignmentforum.org